© 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 EvalsExportsinterp-engineNEWAPI 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. 7-RESID-POST-AA
    11. 8217
    Prev
    Next
    INDEX
    Explanations

    Addressing the reader

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     LSTM
    -0.07
    .swap
    -0.07
     élèves
    -0.07
     actionTypes
    -0.07
    .way
    -0.07
    _FIXED
    -0.07
     Vern
    -0.07
    咱
    -0.07
    أغلب
    -0.07
     hazards
    -0.07
    POSITIVE LOGITS
    from
    0.07
     Please
    0.07
    ```
    0.07
    เศร
    0.07
    ページ
    0.06
    nesia
    0.06
    婪
    0.06
    .openapi
    0.06
    ipeg
    0.06
     please
    0.06
    Activations Density 0.698%

    No Known Activations