© 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. 41082
    Prev
    Next
    INDEX
    Explanations

    download links or legal citations

    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
    Å¡n
    -0.08
    cuci
    -0.08
     dicip
    -0.08
    ,"\
    -0.08
    digest
    -0.08
    enstein
    -0.08
     lesqu
    -0.07
    èĭ
    -0.07
    å®Ļ
    -0.07
    ä¸İåĽ½åĨħ
    -0.07
    POSITIVE LOGITS
    éľĢçĶ¨
    0.07
    inata
    0.06
    /tmp
    0.06
    ç´§å¯Ĩç»ĵåIJĪ
    0.06
    à¤łà¥Ģ
    0.06
    ียà¸ĩ
    0.06
    æĮĤåı·
    0.06
     dile
    0.06
    اÙģتÙĩ
    0.06
    ä¸ĢçĤ¹åĦ¿
    0.06
    Activations Density 0.145%

    No Known Activations