© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 130819
    Prev
    Next
    INDEX
    Explanations

    add

    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
    ographies
    -0.27
    ;element
    -0.26
     swo
    -0.26
    igu
    -0.25
    åĩºåħ¥
    -0.25
    <src
    -0.24
    intree
    -0.24
    ','=','
    -0.23
    atre
    -0.23
    导åħ¥
    -0.23
    POSITIVE LOGITS
    çľĭè¿ĩ
    0.28
    HIR
    0.28
    repr
    0.27
    æĭ¨
    0.26
    Convention
    0.26
    kö
    0.25
    GetInstance
    0.25
    ç¢
    0.25
    çľĭä½ł
    0.24
     tens
    0.24
    Activations Density 0.336%

    No Known Activations