© 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. 32239
    Prev
    Next
    INDEX
    Explanations

    motion and movement

    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
     conveniently
    -0.07
    éĢļè¿ĩç½ij绾
    -0.07
    æľīæ¯Ĵ
    -0.06
    è¿Ľä¸ĢæŃ¥å®ĮåĸĦ
    -0.06
    渴
    -0.06
    åī²
    -0.06
    è¡¥
    -0.06
    ä¸įåłª
    -0.06
     bake
    -0.06
    oot
    -0.06
    POSITIVE LOGITS
    è½»æŁĶ
    0.10
     technique
    0.09
    è¦ģé¢Ĩ
    0.09
    æīĭæ³ķ
    0.09
    åĬĽåº¦
    0.09
    æĮīåİĭ
    0.09
    æĸ¹æ³ķè¿Ľè¡Į
    0.09
     gentle
    0.09
     gently
    0.09
    该æĸ¹æ³ķ
    0.09
    Activations Density 0.042%

    No Known Activations