© 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. 47308
    Prev
    Next
    INDEX
    Explanations

    fetching or carrying

    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
    使èĩªå·±çļĦ
    -0.07
    _PKG
    -0.07
    é¢ĦåĮħè£ħ
    -0.07
    é¼ĵæİĮ
    -0.06
    /js
    -0.06
    大çĤ®
    -0.06
    osph
    -0.06
    hang
    -0.06
    çĭ©
    -0.06
     bench
    -0.06
    POSITIVE LOGITS
    带åĽŀ
    0.11
    è·ijèħ¿
    0.11
    æĬ¥åijĬ
    0.11
    带åİ»
    0.10
     fetching
    0.10
     carrying
    0.10
    éĢģä¿¡
    0.10
    ä¼łè¾¾
    0.10
    æĬ¥åijĬçļĦ
    0.09
    Task
    0.09
    Activations Density 0.103%

    No Known Activations