© 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. 32-TRANSCODER-HP
    7. 43950
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¿ĺä¸įæĺ¯
    -0.27
     realize
    -0.25
    etail
    -0.25
    lias
    -0.24
    getRequest
    -0.24
    åĪĩåħ¥
    -0.24
     perf
    -0.24
    lg
    -0.23
    ,request
    -0.23
    ;</
    -0.23
    POSITIVE LOGITS
    éĴ§
    0.30
     mol
    0.25
    ichtet
    0.24
    /goto
    0.23
    ockets
    0.23
    urs
    0.23
    è±ģ
    0.23
    èĪ«
    0.23
    azine
    0.23
    (stop
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.