© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42492
    Prev
    Next
    INDEX
    Explanations

    URL delimiters

    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
    elf
    -0.07
    REE
    -0.06
    \n
    -0.06
    SES
    -0.06
    .results
    -0.06
    iom
    -0.06
    å¥Īä½ķ
    -0.06
    ropp
    -0.06
    orch
    -0.06
    itz
    -0.06
    POSITIVE LOGITS
    <|box_end|>
    0.12
    ä¼ĹæīĢåij¨çŁ¥
    0.12
    åĬłæĭ¿å¤§
    0.10
    æĸ°åĬłåĿ¡
    0.10
    éĺ¿æĭī伯
    0.10
    缸è¾ħ缸æĪIJ
    0.09
    åħ¢åħ¢ä¸ļä¸ļ
    0.09
    俱ä¹IJéĥ¨
    0.09
    äºĭåįĬåĬŁåĢį
    0.08
    ä¸įåı¯æĢĿè®®
    0.08
    Activations Density 0.262%

    No Known Activations