© 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. 40886
    Prev
    Next
    INDEX
    Explanations

    or longer/later/soon/above/schizophrenia

    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
    æ¥ļæ¥ļ
    -0.08
    èĨĢ
    -0.08
    =:
    -0.07
    èĭ±æĸĩåIJįåŃĹ
    -0.07
    åĮºäººæ°ijæĶ¿åºľ
    -0.07
    aios
    -0.07
    stras
    -0.07
    ä¸Ĭä¸į
    -0.07
    å¾·åŁº
    -0.07
    å¹´å·¥ä½ľ
    -0.07
    POSITIVE LOGITS
    åľ°
    0.08
    é«ĺå±±
    0.08
    ä¸Ģçľ¼
    0.07
    èįī
    0.07
    roso
    0.07
    ä¸ĢåĪĩ
    0.06
    undan
    0.06
    æľĿ
    0.06
    iras
    0.06
    åĺī
    0.06
    Activations Density 0.001%

    No Known Activations