© 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. 34354
    Prev
    Next
    INDEX
    Explanations

    Confucius, stoic, Jedi, Brahmin

    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
    rens
    -0.08
    åįĩåĪĿ
    -0.08
    tures
    -0.08
    orse
    -0.08
    åħ³å¤´
    -0.08
    ëĭĪëĭ¤
    -0.08
    KeyType
    -0.07
    åħ»æ®ĸä¸ĵä¸ļåIJĪä½ľç¤¾
    -0.07
    æĸ°éĹ»è®°èĢħ
    -0.07
    åį³éĢĿ
    -0.07
    POSITIVE LOGITS
    èįĢ
    0.07
    åħ¸ç±į
    0.07
    beeld
    0.07
    åѦèĢħ
    0.07
    æ²»åĽ½
    0.07
    ople
    0.07
    opathic
    0.06
    åĩºèº«çļĦ
    0.06
    åŃŁåŃIJ
    0.06
    ç»ıåħ¸
    0.06
    Activations Density 0.001%

    No Known Activations