© 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. 141502
    Prev
    Next
    INDEX
    Explanations

    Initials

    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
     provisions
    -0.24
    venient
    -0.24
     unr
    -0.24
    .classList
    -0.24
     ||
    -0.23
    aligned
    -0.23
    rances
    -0.23
     apprentices
    -0.23
    ä½ĵ
    -0.23
    NEY
    -0.23
    POSITIVE LOGITS
    icker
    0.28
    omb
    0.28
    æł·çļĦ
    0.27
    OKEN
    0.25
    ocab
    0.25
    екÑĤ
    0.25
    iska
    0.25
    天èĬ±æĿ¿
    0.24
    커
    0.24
    god
    0.24
    Activations Density 3.880%

    No Known Activations