© 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. 19-RESID-POST-AA
    11. 127633
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ercicio
    -0.07
     shows
    -0.07
    Bush
    -0.07
    pr
    -0.07
    .Parse
    -0.07
    曝
    -0.07
    Ohio
    -0.07
     acos
    -0.07
     Bulls
    -0.06
    .GetOrdinal
    -0.06
    POSITIVE LOGITS
    lation
    0.07
     наличии
    0.07
    主要集中
    0.07
     getType
    0.07
    auction
    0.07
     elementType
    0.06
    遗漏
    0.06
    ector
    0.06
    地貌
    0.06
     Nikon
    0.06
    Activations Density 0.084%

    No Known Activations