© 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. 58408
    Prev
    Next
    INDEX
    Explanations

    instructions for lists or examples

    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
    è¢ħ
    -0.07
    ewood
    -0.07
    Lint
    -0.07
    æľ¬åľºæ¯ĶèµĽ
    -0.07
    -fw
    -0.07
    ä¸ĭåIJĮ
    -0.06
    ä¸įåIJĮæŶ
    -0.06
     íİ
    -0.06
    æĿ¥ä¹ĭ
    -0.06
    agues
    -0.06
    POSITIVE LOGITS
    ulina
    0.07
    trom
    0.07
    ussen
    0.06
    å¨ĩ妻
    0.06
     foregoing
    0.06
     principles
    0.06
    _extractor
    0.06
     theme
    0.06
     Principles
    0.06
    èĭ¦è¾£
    0.06
    Activations Density 0.020%

    No Known Activations