© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17165
    Prev
    Next
    INDEX
    Explanations

    mechanical or device operations

    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
    BoundingBox
    -0.07
    æľīè¿Ļæł·çļĦ
    -0.07
    jÄħ
    -0.07
    ascin
    -0.07
     chân
    -0.07
    cors
    -0.07
    –and
    -0.07
    czyn
    -0.07
     übrigens
    -0.07
    èĢĮ对äºİ
    -0.07
    POSITIVE LOGITS
    æ²Ľ
    0.07
    engg
    0.07
    /latest
    0.07
    éĤ£æĺ¯æĪij
    0.06
    olla
    0.06
    缴æİ¥æĪĸ
    0.06
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.06
     altrettanto
    0.06
    éĤ£äºĽ
    0.06
     Kil
    0.06
    Activations Density 0.096%

    No Known Activations