© 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. 56450
    Prev
    Next
    INDEX
    Explanations

    hands gesturing or grasping

    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
     Ñĥмол
    -0.08
    quilla
    -0.08
    æĢ§åŃIJ
    -0.08
    çĥĪ
    -0.08
    гон
    -0.08
    è·ijå¾Ĺ
    -0.08
    é½Ĵ
    -0.08
    èĦijè¢ĭ
    -0.07
    اشت
    -0.07
    çīĻ
    -0.07
    POSITIVE LOGITS
     gesture
    0.07
    ä¸ĭæĦıè¯Ĩ
    0.07
    ovel
    0.07
     اÙĦÙĬد
    0.07
     grasp
    0.07
    ä¸ĭæĦıè¯ĨçļĦ
    0.07
    moni
    0.07
    伸
    0.07
    avi
    0.07
    icap
    0.07
    Activations Density 0.048%

    No Known Activations