© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 11910
    Prev
    Next
    INDEX
    Explanations

    War and military history

    np_max-act · gemini-2.0-flash

    explicit pornographic content, especially extreme, violent, and taboo sexual themes (e.g., coercion, degradation, and fetishized acts).

    oai_token-act-pair · gpt-5Triggered by @vetterc0

    highly explicit pornographic and abusive sexual content, especially graphic violence and taboo scenarios.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ("/
    -0.07
     Challenger
    -0.07
     AAA
    -0.07
    殃
    -0.07
     grocery
    -0.07
     стоит
    -0.06
    蓋
    -0.06
     qry
    -0.06
     đặt
    -0.06
    🛬
    -0.06
    POSITIVE LOGITS
    menus
    0.07
     reconc
    0.07
    -compatible
    0.06
    byterian
    0.06
    _present
    0.06
    eight
    0.06
     calendars
    0.06
    .jdesktop
    0.06
    _sex
    0.06
     compuls
    0.06
    Activations Density 23.395%

    No Known Activations