© 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. 22707
    Prev
    Next
    INDEX
    Explanations

    information for specific items

    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
    undos
    -0.07
     Weinstein
    -0.07
    ÄĽj
    -0.07
    ä¸įåıij
    -0.07
    ç®Ĺ
    -0.07
    èŀ
    -0.07
    LAST
    -0.07
    åİŁåĪĽä½ľåĵģ
    -0.07
     Sanford
    -0.06
    åĪĽéĢłæĿ¡ä»¶
    -0.06
    POSITIVE LOGITS
    æģĨ
    0.07
    å°ĶåŁº
    0.07
    åĽŀ家äºĨ
    0.06
    )::
    0.06
    ourd
    0.06
    heimer
    0.06
    éĤ¢
    0.06
    ÛĮکا
    0.06
    itti
    0.06
    krim
    0.06
    Activations Density 0.021%

    No Known Activations