© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 126905
    Prev
    Next
    INDEX
    Explanations

    Website code/text artifacts

    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_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
    Negative Logits
     teaspoon
    -0.07
    Wow
    -0.07
    Dar
    -0.06
    Ont
    -0.06
     Stream
    -0.06
     produits
    -0.06
     Dt
    -0.06
     CT
    -0.06
     ident
    -0.06
    -ce
    -0.06
    POSITIVE LOGITS
    JSGlobal
    0.08
    生产总
    0.08
    selected
    0.07
    OTTOM
    0.07
    '](
    0.07
    戋
    0.07
    :${
    0.07
    YG
    0.07
     bols
    0.07
     walls
    0.07
    Activations Density 0.011%

    No Known Activations