© 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. 11-RESID-POST-AA
    11. 4217
    Prev
    Next
    INDEX
    Explanations

    copyright symbol

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    אנשי
    -0.08
     për
    -0.07
    癃
    -0.06
    ראש
    -0.06
    irable
    -0.06
    儲
    -0.06
    �
    -0.06
    能把
    -0.06
    首发
    -0.06
    tain
    -0.06
    POSITIVE LOGITS
     ("/
    0.07
     nerve
    0.07
    Regression
    0.07
    eil
    0.07
     funktion
    0.07
    针
    0.07
    ู่
    0.06
     Ere
    0.06
    .bio
    0.06
     Brick
    0.06
    Activations Density 0.001%

    No Known Activations