© 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. 75239
    Prev
    Next
    INDEX
    Explanations

    PL

    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
    (link
    -0.08
    顶层设计
    -0.08
     skyline
    -0.07
     thesis
    -0.07
    (lock
    -0.07
     Thesis
    -0.07
     Farrell
    -0.07
    ידה
    -0.07
    timing
    -0.07
    _tool
    -0.07
    POSITIVE LOGITS
     public
    0.07
    接送
    0.07
    مات
    0.07
    省市
    0.07
    Republican
    0.06
     MOUSE
    0.06
    男女
    0.06
     `[
    0.06
     band
    0.06
    幫
    0.06
    Activations Density 0.015%

    No Known Activations