© 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. 22270
    Prev
    Next
    INDEX
    Explanations

    directly from

    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
    ãģľ
    -0.08
    æłĩåĩĨè¦ģæ±Ĥ
    -0.07
    继ç»Ń使çĶ¨
    -0.07
    ignant
    -0.07
    IfExists
    -0.07
    worthy
    -0.07
     qa
    -0.07
    æĶ¯æ°Ķ管çĤİ
    -0.07
     worthy
    -0.07
    -worthy
    -0.07
    POSITIVE LOGITS
    æĪĸ缴æİ¥
    0.12
    缴æİ¥
    0.11
     Direct
    0.10
    çļĦ缴æİ¥
    0.10
    .direct
    0.09
    缴æİ¥çļĦ
    0.09
     directly
    0.09
     Ùħباشر
    0.09
     اÙĦÙħباشر
    0.09
    æĺ¯çĽ´æİ¥
    0.09
    Activations Density 0.017%

    No Known Activations