© 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. 31944
    Prev
    Next
    INDEX
    Explanations

    classified type

    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
    wald
    -0.07
     coinc
    -0.06
     mont
    -0.06
    æľ¬åľ°
    -0.06
     Newly
    -0.06
     sympath
    -0.06
    çĶ±æĿ¥
    -0.06
    å·įå·į
    -0.06
     newly
    -0.05
    èĴĻ
    -0.05
    POSITIVE LOGITS
    convert
    0.11
    ä½ĵè£ģ
    0.11
    ä¸įåIJĮç±»åŀĭçļĦ
    0.10
    ?type
    0.10
    Convert
    0.10
     Convert
    0.09
    ç±»åŀĭçļĦ
    0.09
    à¸Ľà¸£à¸°à¹Ģà¸łà¸Ĺ
    0.09
     convert
    0.09
    ElementType
    0.09
    Activations Density 0.457%

    No Known Activations