© 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. 97421
    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
    Not in Any Lists

    No Comments

    Negative Logits
    -city
    -0.27
    -ie
    -0.26
    oken
    -0.25
    åŁİå¸Ĥ建设
    -0.25
    bery
    -0.25
    lasses
    -0.25
     hud
    -0.24
    orary
    -0.23
    -town
    -0.23
     Ping
    -0.23
    POSITIVE LOGITS
    æĸľ
    0.28
     SqlDbType
    0.25
    ä¸ĩåħĥ以ä¸Ĭ
    0.25
    åŁĭ
    0.25
     rest
    0.24
    躺
    0.24
     proved
    0.24
    éĻ¢éĻ¢å£«
    0.23
     drift
    0.23
    inte
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.