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

    Neuronpedia

    Jacobian LensNEW
    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. 118043
    Prev
    Next
    INDEX
    Explanations

    adult content

    np_max-act · gemini-2.0-flash

    explicit adult-content keywords and pornographic category/tag jargon, including sexual slurs.

    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
    ascending
    -0.07
    Cascade
    -0.07
    ]:↵↵↵
    -0.07
     scaffold
    -0.07
    (Local
    -0.07
    恍
    -0.07
    代码
    -0.07
     Charg
    -0.07
     supreme
    -0.07
    _large
    -0.07
    POSITIVE LOGITS
     pelos
    0.07
    'hui
    0.07
    �
    0.07
     sooner
    0.06
     bool
    0.06
    chet
    0.06
    Backdrop
    0.06
    ﲬ
    0.06
     Ş
    0.06
    ẳng
    0.06
    Activations Density 6.643%

    No Known Activations