© 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. 64182
    Prev
    Next
    INDEX
    Explanations

    (

    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
    éĹ·
    -0.25
    -schema
    -0.25
    -strip
    -0.25
    ebb
    -0.25
    åģļ
    -0.25
    uje
    -0.25
    ibri
    -0.24
     womb
    -0.23
    Strip
    -0.23
    arez
    -0.23
    POSITIVE LOGITS
    productName
    0.32
    idl
    0.27
     Pav
    0.27
    ä¸Ĭ线
    0.26
    anker
    0.25
    ↵        ↵        ↵
    0.24
    毫
    0.24
    _so
    0.24
     gre
    0.23
     productName
    0.23
    Activations Density 11.327%

    No Known Activations