© 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. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 112907
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è¡¡
    -0.27
    rier
    -0.26
    SYS
    -0.25
    é¼»åŃIJ
    -0.24
    beck
    -0.24
    hol
    -0.24
    woman
    -0.23
    Caption
    -0.22
    idon
    -0.22
    crap
    -0.21
    POSITIVE LOGITS
    ç¯ĩ
    0.27
    .qq
    0.25
    ibrary
    0.25
    ooks
    0.23
    æĿĤå¿Ĺ
    0.23
     earlier
    0.23
    (**
    0.23
    ased
    0.22
     spy
    0.22
     mean
    0.21
    Activations Density 0.062%

    No Known Activations

    This feature has no known activations.