Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 27-RESID-POST-AA
    6. 130997
    Prev
    Next
    INDEX
    Explanations

    heroes and legends

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Workspace
    -0.08
     kn
    -0.07
     tricky
    -0.07
     Eleanor
    -0.07
    Western
    -0.07
    Positions
    -0.07
     geography
    -0.07
     waypoints
    -0.07
     assignments
    -0.07
    handles
    -0.07
    POSITIVE LOGITS
    箦
    0.07
    MOTE
    0.07
    提议
    0.07
    ToShow
    0.07
    專家
    0.06
     FAIL
    0.06
    OrFail
    0.06
    $model
    0.06
    .FontStyle
    0.06
    fails
    0.06
    Activations Density 0.078%

    No Known Activations