© 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. 31716
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
    asar
    -0.08
    æµ®èĤ¿
    -0.08
    .bootstrap
    -0.08
     cadr
    -0.07
    åıĹåĪ°çļĦ
    -0.07
    åıĹåĩī
    -0.07
    æīĵæ°´
    -0.06
    å¾ĭå¸Ī解çŃĶ
    -0.06
    æ¯Ķèĩªå·±
    -0.06
    arnos
    -0.06
    POSITIVE LOGITS
     equations
    0.09
    æĸ¹ç¨ĭ
    0.09
     equation
    0.09
     lautet
    0.08
     rÃłng
    0.08
     coordinates
    0.08
    约æĿŁ
    0.08
    ibas
    0.08
    æĸ¹ç¨ĭå¼ı
    0.08
    лиÑĢÑĥ
    0.08
    Activations Density 0.012%

    No Known Activations