© 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. 1122
    Prev
    Next
    INDEX
    Explanations

    hand, palm, and wrist parts

    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
    å±ģèĤ¡
    -0.08
     caval
    -0.07
    ropa
    -0.07
    èĤļçļ®
    -0.07
     blankets
    -0.07
    upu
    -0.07
    é¸¡æ¯Ľ
    -0.07
    èĨĺ
    -0.07
    èĤļåŃIJéĩĮ
    -0.07
     Tall
    -0.07
    POSITIVE LOGITS
    æı¡
    0.13
    èħķ
    0.12
     grip
    0.11
     forearm
    0.11
     wrist
    0.11
    æīĭçļĦ
    0.10
    æĭĩæĮĩ
    0.10
    ç´§æı¡
    0.10
    äºĶæĮĩ
    0.10
     fingers
    0.10
    Activations Density 0.164%

    No Known Activations