© 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. 142256
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    dfa
    -0.27
    caffold
    -0.26
    aeda
    -0.26
    olars
    -0.25
    åŀĦ
    -0.24
     Elephant
    -0.24
    缴åįĩ
    -0.24
    ize
    -0.24
    reon
    -0.23
    ç¬
    -0.23
    POSITIVE LOGITS
    ili
    0.26
    æĭĽ
    0.26
    okie
    0.25
    fer
    0.25
    meric
    0.24
    æĥ³åĥı
    0.24
    ç¢Ľ
    0.24
    xit
    0.23
    æĥ³è±¡
    0.23
    bro
    0.23
    Activations Density 0.174%

    No Known Activations

    This feature has no known activations.