© 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. 56048
    Prev
    Next
    INDEX
    Explanations

    optimization problem

    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
    ваÑĩ
    -0.07
    æĥķ
    -0.07
    ä¸Ĭ课æŶ
    -0.07
    ä¸į管æĺ¯
    -0.07
    æīįè¡Į
    -0.07
    áÄį
    -0.07
    *Math
    -0.07
    iquement
    -0.07
    ç»ıå®¡æŁ¥
    -0.07
    ardino
    -0.07
    POSITIVE LOGITS
    æijĨ
    0.07
    ä¼´
    0.06
     depending
    0.06
    æ²Į
    0.06
     Spe
    0.06
    便æľī
    0.06
     asymmetric
    0.06
    ндÑĸ
    0.06
    (TYPE
    0.06
    maar
    0.06
    Activations Density 0.006%

    No Known Activations