© 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. 129672
    Prev
    Next
    INDEX
    Explanations

    that

    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
    burgh
    -0.25
    夺
    -0.24
    çĮª
    -0.24
    Navigator
    -0.24
    .onStart
    -0.24
    .go
    -0.23
    (od
    -0.23
    æľĽ
    -0.23
    ioni
    -0.23
     Directions
    -0.23
    POSITIVE LOGITS
    åĨħåľ¨
    0.29
    åħ¶ä»ĸ人
    0.26
    身ä½ĵåģ¥åº·
    0.26
    驸
    0.26
    åĽ¢åijĺ
    0.26
    asurable
    0.25
    æĸ°ä¸ī
    0.25
    ,body
    0.25
     cumulative
    0.25
    秦çļĩ
    0.24
    Activations Density 28.327%

    No Known Activations