© 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. 20-TRANSCODER-HP
    7. 130955
    Prev
    Next
    INDEX
    Explanations

    programming/logic/settings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    rale
    -0.29
    ITED
    -0.27
    诰
    -0.26
    æĹłéĻIJ
    -0.25
    metric
    -0.25
    çļĦæĥħ
    -0.24
    pretty
    -0.24
     Nin
    -0.24
    .splitext
    -0.24
    *f
    -0.24
    POSITIVE LOGITS
    edImage
    0.32
    CCI
    0.26
    uur
    0.26
    abus
    0.25
    è¿ĺèĥ½
    0.25
    /cloud
    0.24
    æł¹æľ¬
    0.24
    erset
    0.24
     ë¬¼ë¡ł
    0.24
     Both
    0.24
    Activations Density 90.064%

    No Known Activations