© 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. 51611
    Prev
    Next
    INDEX
    Explanations

    punctuation separation

    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
    åĬłæĭ¿å¤§
    -0.07
    esson
    -0.07
     Virtu
    -0.07
    èĥ¡æĢĿ
    -0.07
    ä¼ĹæīĢåij¨çŁ¥
    -0.07
    æĸ°åĬłåĿ¡
    -0.07
    åĴĮçĶ°
    -0.07
    _VIRTUAL
    -0.07
    éĤ£é¢Ĺ
    -0.07
    oldt
    -0.06
    POSITIVE LOGITS
    èѬå¦Ĥ
    0.07
    uum
    0.07
    arin
    0.07
    acin
    0.07
    -controls
    0.07
    UnderTest
    0.07
    ')[
    0.06
    anine
    0.06
    rompt
    0.06
    ))[
    0.06
    Activations Density 0.041%

    No Known Activations