© 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. 63977
    Prev
    Next
    INDEX
    Explanations

    tables, graphs, and data

    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
    isses
    -0.27
    izable
    -0.25
    ihan
    -0.24
    ãĤ¿ãĥ¼
    -0.24
    callable
    -0.24
    Clause
    -0.23
     Clause
    -0.23
    icles
    -0.23
    çļĦäºĭæĥħ
    -0.23
    lich
    -0.23
    POSITIVE LOGITS
    计éĩı
    0.27
    alus
    0.27
    ç©
    0.26
    ---</
    0.24
    EncodingException
    0.24
     ник
    0.23
    ÑĢон
    0.23
     bÆ°á»Ľc
    0.23
    è¿ĺæľīä¸ĢäºĽ
    0.23
    afe
    0.23
    Activations Density 7.140%

    No Known Activations