© 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. 22-TRANSCODER-HP
    7. 111562
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    []>↵
    -0.26
    åįļæĸĩ
    -0.25
    $")↵
    -0.25
    [D
    -0.24
    身影
    -0.24
    åķĥ
    -0.24
    ç¾İ女
    -0.24
    é¢ĺ主
    -0.23
    åħļåĴĮ
    -0.23
    [P
    -0.23
    POSITIVE LOGITS
    angkan
    0.27
    hole
    0.25
    FTA
    0.24
    Repair
    0.24
    MIC
    0.23
    strup
    0.23
     GOT
    0.23
    motion
    0.23
    .%
    0.23
    migration
    0.23
    Activations Density 0.015%

    No Known Activations