© 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. 7436
    Prev
    Next
    INDEX
    Explanations

    translation initiation

    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
    çº¸å¼ł
    -0.07
    ä¸ĩå¹´
    -0.07
    è®®ç¨ĭ
    -0.07
    anjian
    -0.07
     acer
    -0.07
    agian
    -0.07
    ález
    -0.06
    æĹ¥åĪ°
    -0.06
    å¾Ĺ罪
    -0.06
    calar
    -0.06
    POSITIVE LOGITS
    ommel
    0.08
    åħ¬åı¸æݨèįIJ
    0.08
    å¼Ģå§ĭåIJİ
    0.07
    çĮľä½łåĸľæ¬¢
    0.07
     Pearce
    0.07
    _startup
    0.07
    ä¸įçł´
    0.07
    大ä¸ĸçķĮ
    0.07
    uzzi
    0.06
    åĬ«
    0.06
    Activations Density 0.021%

    No Known Activations