© 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. 30-TRANSCODER-HP
    7. 95051
    Prev
    Next
    INDEX
    Explanations

    injuries and body parts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ewear
    -0.26
    minate
    -0.26
    rades
    -0.26
     Sachs
    -0.26
    è´ŀ
    -0.25
     Crime
    -0.25
    çī©çIJĨ
    -0.24
    çķ´
    -0.24
    æĢ»éĺŁ
    -0.24
    lee
    -0.23
    POSITIVE LOGITS
     toe
    0.29
    åĽ½éĻħæľºåľº
    0.29
    æ´ĹèĦ¸
    0.27
    ki
    0.27
     leg
    0.26
     fell
    0.26
     noses
    0.26
    AMIL
    0.25
     fall
    0.25
     Gen
    0.25
    Activations Density 0.788%

    No Known Activations