© 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. 63860
    Prev
    Next
    INDEX
    Explanations

    Names

    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
    幸好
    -0.28
    айÑĤе
    -0.27
    ç«ĭåį³
    -0.25
    Fine
    -0.25
    UTO
    -0.24
    åķ¬
    -0.24
    AAA
    -0.23
    Ut
    -0.23
    ivamente
    -0.23
    ame
    -0.23
    POSITIVE LOGITS
    getResponse
    0.27
     mart
    0.24
    磮
    0.24
    vip
    0.24
     $?
    0.24
     deemed
    0.23
    hir
    0.23
     querying
    0.23
    äºĽ
    0.23
    ä¼łæĦŁ
    0.23
    Activations Density 0.987%

    No Known Activations