© 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. 141855
    Prev
    Next
    INDEX
    Explanations

    Programming/problem-solving

    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
    iram
    -0.25
    -actions
    -0.24
     Pixels
    -0.24
    æ·Ŀ
    -0.24
     Matters
    -0.24
    vals
    -0.24
    addAction
    -0.24
    tps
    -0.23
    _consts
    -0.23
    åĽłä¸ºä»ĸ
    -0.23
    POSITIVE LOGITS
    ç¡ķ士åѦä½į
    0.26
    å®ĥ
    0.25
    t
    0.25
    ong
    0.25
    æĹ©æĻļ
    0.25
    ç«
    0.25
     din
    0.25
    设ç«ĭ
    0.24
    该åİ¿
    0.24
    oti
    0.24
    Activations Density 46.274%

    No Known Activations