© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34757
    Prev
    Next
    INDEX
    Explanations

    Field of the Invention

    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
     Ñģлед
    -0.08
    leta
    -0.08
    ä¸ĭåĪĹ说æ³ķ
    -0.07
    جاÙĨ
    -0.07
    opc
    -0.07
    afka
    -0.07
    ä¸ĭåĪĹ
    -0.07
    iggs
    -0.07
     élég
    -0.07
    -Ta
    -0.07
    POSITIVE LOGITS
    ç®Ģè¿°
    0.07
    ner
    0.07
    bounding
    0.06
    对æĸ¹çļĦ
    0.06
     Cald
    0.06
    esser
    0.06
    acceptable
    0.06
    çļĦéĤ£äºĽ
    0.06
     tur
    0.06
    æ±Ĥè´Ń
    0.06
    Activations Density 0.001%

    No Known Activations