© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21115
    Prev
    Next
    INDEX
    Explanations

    closing bracket equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ry
    -0.07
    athon
    -0.07
    人
    -0.07
    sWith
    -0.07
    ductor
    -0.07
    rika
    -0.07
    rium
    -0.07
    <|box_end|>
    -0.07
    enzie
    -0.07
    ging
    -0.06
    POSITIVE LOGITS
    ãĥ³
    0.09
    othe
    0.08
    oriously
    0.08
    ally
    0.08
    elon
    0.08
    æĸ°åĬłåĿ¡
    0.08
    educt
    0.08
    åĬłæĭ¿å¤§
    0.08
    ä¸įåı¯æĢĿè®®
    0.08
    åĭĩå¾Ģ缴åīį
    0.08
    Activations Density 0.008%

    No Known Activations