© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20470
    Prev
    Next
    INDEX
    Explanations

    legal notices and proceedings

    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
    äºĭåįĬåĬŁåĢį
    -0.10
    ænd
    -0.07
    akit
    -0.07
    .gnu
    -0.07
    æ¢ĵ
    -0.07
    æİ´
    -0.07
    èĦıèħij
    -0.07
    actly
    -0.07
    æ³ķç½ij
    -0.07
    天åŃIJ
    -0.07
    POSITIVE LOGITS
    æľīåħ³äºĭ项
    0.07
    两件
    0.07
    éĹľæĸ¼
    0.07
    åIJijä¸ŃåĽ½
    0.07
    å¯¹åľ¨
    0.07
    ÙĬÙĩ
    0.07
    æıIJ请
    0.07
    çŃĶå¤į
    0.07
    转åıij
    0.07
    _magic
    0.06
    Activations Density 0.018%

    No Known Activations