© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 64239
    Prev
    Next
    INDEX
    Explanations

    Code/Documentation snippets

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ewidth
    -0.24
    errick
    -0.24
    adays
    -0.23
    ibrary
    -0.23
    GroupId
    -0.23
    .outer
    -0.23
    çĿļ
    -0.23
    ingu
    -0.23
    帽åŃIJ
    -0.23
     Alleg
    -0.22
    POSITIVE LOGITS
    è´¨
    0.27
    vos
    0.27
    LOT
    0.25
    upon
    0.25
    chio
    0.25
    efd
    0.25
    rv
    0.24
     mass
    0.24
    æĬ½
    0.24
    é³ħ
    0.23
    Activations Density 77.804%

    No Known Activations