© 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. 130090
    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
    ç¢Ĺ
    -0.28
     previously
    -0.27
    ç²Ł
    -0.26
    鸦
    -0.25
    åIJĥå®Į
    -0.25
    _fraction
    -0.25
    èĪ«
    -0.24
     chicken
    -0.24
    _SUP
    -0.24
     Narr
    -0.24
    POSITIVE LOGITS
    utherland
    0.27
    ulary
    0.26
    utow
    0.25
    ères
    0.25
    ÙĬرة
    0.24
     mont
    0.24
     mounts
    0.24
    >{"
    0.24
    InnerText
    0.24
    OLUTE
    0.23
    Activations Density 6.109%

    No Known Activations