© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 23711
    Prev
    Next
    INDEX
    Explanations

    bot conversations

    np_max-act · gemini-2.0-flash

    assistant self-introductions and capability statements, especially first-person (“I”, “my”) references and mentions of being an AI/language model.

    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
     ко
    -0.08
    Ford
    -0.07
    [row
    -0.07
    semb
    -0.07
     kW
    -0.07
    STEM
    -0.07
     Ling
    -0.06
    しておく
    -0.06
    飽
    -0.06
    DTD
    -0.06
    POSITIVE LOGITS
    _MESH
    0.07
    천
    0.07
     cylindrical
    0.07
     projections
    0.07
     Transmission
    0.07
     plastic
    0.07
    uyện
    0.06
    ATTERN
    0.06
    美丽乡村
    0.06
    curve
    0.06
    Activations Density 0.416%

    No Known Activations