© 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. 43411
    Prev
    Next
    INDEX
    Explanations

    malfunctioning or inoperative

    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
    enj
    -0.10
    æł¼å°Ķ
    -0.08
    ä¹ĭéŨ
    -0.08
    [__
    -0.08
    ืà¸Ńà¸ĩ
    -0.08
    unj
    -0.07
    heb
    -0.07
    aget
    -0.07
    stderr
    -0.07
    vern
    -0.07
    POSITIVE LOGITS
    åľ¨è¿Ļç§įæĥħåĨµä¸ĭ
    0.09
    è¿Ļç§įæĥħåĨµä¸ĭ
    0.09
    è¿ĻæŶ
    0.09
    æѤæŶ
    0.08
    éĤ£æŶ
    0.08
    éĢĻæĻĤ
    0.08
    è¿ĻæŶåĢĻ
    0.08
    è¿Ļ个æŶåĢĻ
    0.07
    æº
    0.07
     supposed
    0.07
    Activations Density 0.047%

    No Known Activations