© 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. 11-RESID-POST-AA
    11. 130178
    Prev
    Next
    INDEX
    Explanations

    code relating to UI

    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
    Negative Logits
     discount
    -0.07
    𝘋
    -0.07
    кцион
    -0.07
    dex
    -0.07
    Detalle
    -0.06
    טקס
    -0.06
    釐
    -0.06
    Desc
    -0.06
    上升
    -0.06
    Compare
    -0.06
    POSITIVE LOGITS
    شهاد
    0.07
     htons
    0.07
    ,V
    0.07
     useParams
    0.07
    くらい
    0.06
     MongoClient
    0.06
    (setq
    0.06
     engine
    0.06
     Kit
    0.06
    _LAT
    0.06
    Activations Density 0.046%

    No Known Activations