© 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. 31669
    Prev
    Next
    INDEX
    Explanations

    DAO method, mysql log, metal production, Fat staining

    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
    åı¯åĪ©çĶ¨
    -0.07
    ivr
    -0.07
    æĺ¯ä»Ģä¹Īæł·çļĦ
    -0.07
    à®ķà¯ģ
    -0.07
    åı¯éĢĤå½ĵ
    -0.07
    åľ¨çº¿åĴ¨è¯¢
    -0.06
    mans
    -0.06
    åıĮæĸ¹å½ĵäºĭ人
    -0.06
    ogna
    -0.06
    éĤ£åı¯
    -0.06
    POSITIVE LOGITS
    åĺĽ
    0.09
    ä¹Łåı¯çĽ´æİ¥
    0.08
     ìĿ´ì²ĺëŁ¼
    0.07
     insomma
    0.07
    å°±è¿Ļæł·
    0.07
     thus
    0.07
    å°±è¿Ļä¹Ī
    0.07
    è¶Ĭæĥ³
    0.07
    rau
    0.07
    åijľ
    0.07
    Activations Density 0.030%

    No Known Activations