© 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. 96902
    Prev
    Next
    INDEX
    Explanations

    how

    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
     {[
    -0.28
     Usa
    -0.26
    ç¬ij声
    -0.25
    aley
    -0.25
    prot
    -0.24
     ÙĪبÙĬÙĨ
    -0.24
    аÑĤÑĥÑĢ
    -0.24
    .more
    -0.24
     æĽ´
    -0.24
    byn
    -0.23
    POSITIVE LOGITS
    å¦Ĥä½ķ
    0.31
    æĪĽ
    0.28
    çªĸ
    0.28
     '
    0.26
    壮
    0.26
    åľ¨æł¡
    0.25
     psychotic
    0.25
     squared
    0.25
    æĸ°çīĪ
    0.25
    ฬ
    0.25
    Activations Density 0.887%

    No Known Activations