© 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. 63423
    Prev
    Next
    INDEX
    Explanations

    family history

    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
    enc
    -0.26
    _INCLUDED
    -0.24
    shal
    -0.24
     hend
    -0.24
     inputValue
    -0.24
    _NR
    -0.23
    icc
    -0.23
    lon
    -0.23
    ActionCreators
    -0.23
    incer
    -0.23
    POSITIVE LOGITS
    为主çļĦ
    0.29
    æŀ¢
    0.27
    kers
    0.26
    åĽŀæĬ¥
    0.26
    -question
    0.26
    示æĦı
    0.26
    phet
    0.26
    ä¿Ŀ
    0.24
    quist
    0.24
    ä¾ĿéĿł
    0.24
    Activations Density 2.660%

    No Known Activations