© 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. 25-TRANSCODER-HP
    7. 109377
    Prev
    Next
    INDEX
    Explanations

    code and technical content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     tit
    -0.29
    ilities
    -0.27
    .yahoo
    -0.26
    uria
    -0.25
    <src
    -0.25
    å¾Ĺ太
    -0.25
    çļĦæĦŁæĥħ
    -0.25
    SURE
    -0.24
    umpt
    -0.24
    ì¿ł
    -0.24
    POSITIVE LOGITS
    -round
    0.35
    -percent
    0.33
    -member
    0.33
    -solid
    0.31
    -sided
    0.31
    -important
    0.31
    -per
    0.30
    -in
    0.30
    -point
    0.30
    -fiction
    0.30
    Activations Density 0.980%

    No Known Activations