© 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. 64498
    Prev
    Next
    INDEX
    Explanations

    actions involving physical interaction

    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
     shouts
    -0.07
    è¡Į驶æŶ
    -0.07
    gaard
    -0.07
    汪汪
    -0.07
    rove
    -0.06
    ä¹ł
    -0.06
    ç²ªæ±ł
    -0.06
    erville
    -0.06
    aison
    -0.06
    skraft
    -0.06
    POSITIVE LOGITS
    åıĪä¸Ģ
    0.07
    ä»ĬæĹ¥çļĦ
    0.06
    æĮ½
    0.06
    åİŁè£ħè¿Ľåı£
    0.06
    çļĦæīĭ
    0.06
     Reflex
    0.06
    (peer
    0.06
    opportun
    0.06
    ëĭ´
    0.06
    ä¸įåľ¨æĦı
    0.06
    Activations Density 0.060%

    No Known Activations