© 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. 107676
    Prev
    Next
    INDEX
    Explanations

    code related text

    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
     hum
    -0.27
     Hum
    -0.26
     Zy
    -0.25
    odem
    -0.25
    hum
    -0.25
    ä¸įæĿ¥
    -0.25
    records
    -0.25
    capital
    -0.24
     FOOT
    -0.23
    èĬĻèĵī
    -0.23
    POSITIVE LOGITS
     ÑĤомÑĥ
    0.24
    outube
    0.24
    yal
    0.23
    ér
    0.23
    管çIJĨå·¥ä½ľ
    0.23
    çļĦåħ³ç³»
    0.23
    âĨĸ
    0.23
     Safari
    0.23
    fad
    0.23
    æķĻç»ĥ
    0.23
    Activations Density 96.064%

    No Known Activations