© 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. 64692
    Prev
    Next
    INDEX
    Explanations

    right leg movements

    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
    efeld
    -0.07
    fallen
    -0.07
    map
    -0.07
     static
    -0.07
     Map
    -0.07
     fallen
    -0.07
    æĪ·
    -0.07
    æľīçIJĨ
    -0.06
     parsed
    -0.06
     mapped
    -0.06
    POSITIVE LOGITS
    ä¸İä¼Ĺ
    0.08
    æĥĬå¿ĥåĬ¨
    0.08
    çĭ¬ä¸ĢæĹł
    0.08
    erator
    0.08
     ìĿ´ìļ©íķĺìŬ
    0.08
    anela
    0.07
    ä»Ĭ天è¦ģ
    0.07
    LBL
    0.07
    ä½łæĺ¯æĪij
    0.07
    æĶ¹ä¸º
    0.07
    Activations Density 0.003%

    No Known Activations