© 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. 27802
    Prev
    Next
    INDEX
    Explanations

    residence

    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
    纪
    -0.09
    arrer
    -0.07
    ETS
    -0.07
    .abort
    -0.07
    elyn
    -0.07
    å¤įåĪ¶æĪĸ
    -0.06
    æĪĸåĪ©çĶ¨
    -0.06
    ç»İ
    -0.06
    eler
    -0.06
    eli
    -0.06
    POSITIVE LOGITS
    èĢĮ对äºİ
    0.10
    اعدة
    0.09
     ê·¸ëłĩì§Ģ
    0.09
    åĮºéķ¿
    0.09
    èĢĮéļıçĿĢ
    0.08
    ä½Ĩ对äºİ
    0.08
    åĪ°æĻļ
    0.08
    æīĵå¥½åŁºç¡Ģ
    0.07
    -region
    0.07
    ä½ĨéļıçĿĢ
    0.07
    Activations Density 0.147%

    No Known Activations