© 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. 141391
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    èµ·
    -0.28
    éħį
    -0.27
    å¥Ķ
    -0.26
    ç»Ĭ
    -0.26
    oland
    -0.26
     ë°°
    -0.25
     incur
    -0.25
    lang
    -0.25
    çĿĢ
    -0.24
     franc
    -0.24
    POSITIVE LOGITS
    ungle
    0.28
    duk
    0.28
    为客æĪ·
    0.27
    好åĩłä¸ª
    0.25
    [ix
    0.24
    (ix
    0.24
    漶
    0.23
    ä¹Łæľīå¾Īå¤ļ
    0.23
    meer
    0.23
     palms
    0.23
    Activations Density 6.315%

    No Known Activations