© 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. 47775
    Prev
    Next
    INDEX
    Explanations

    vague or generic terms

    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
    ä¸įåIJĮæŶ
    -0.07
    antino
    -0.07
    oop
    -0.07
    pit
    -0.06
    agram
    -0.06
     Eun
    -0.06
    ä¸¥æł¼æĮīçħ§
    -0.06
    åį«å£«
    -0.06
    éļ¾åħ³
    -0.06
    egram
    -0.06
    POSITIVE LOGITS
     vague
    0.13
    /general
    0.13
     vaguely
    0.12
    æ³Ľ
    0.12
    笼
    0.11
    模ç³Ĭ
    0.10
     generic
    0.10
    ç¼¥ç¼Ī
    0.10
    generic
    0.10
    æĬ½è±¡
    0.09
    Activations Density 0.034%

    No Known Activations