© 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. 141551
    Prev
    Next
    INDEX
    Explanations

    URLs, product names, code

    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
    lays
    -0.25
    帰ãĤĬ
    -0.24
     бÑĥмаг
    -0.24
     Kills
    -0.24
    è·ŁçĿĢ
    -0.24
    ort
    -0.24
    .GetInt
    -0.24
    èIJ½åħ¥
    -0.23
    åīįåįģ
    -0.23
    se
    -0.23
    POSITIVE LOGITS
    åĨī
    0.28
    迳
    0.26
    ONUS
    0.25
    üns
    0.25
     Bá
    0.24
    ä¸įå®ļ
    0.24
     Bicycle
    0.24
    æŃ¥
    0.23
    ç«¥
    0.23
     ath
    0.23
    Activations Density 11.652%

    No Known Activations