© 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. 7089
    Prev
    Next
    INDEX
    Explanations

    landing around

    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
    Negative Logits
    itano
    -0.07
     Thou
    -0.07
    tp
    -0.07
    ä¸į说
    -0.06
    èĢ¿
    -0.06
    hare
    -0.06
     oce
    -0.06
     blas
    -0.06
    ppen
    -0.06
    Ïĥμ
    -0.06
    POSITIVE LOGITS
    ä¸įèĭŁ
    0.08
     intrinsic
    0.08
    uthor
    0.08
     inherently
    0.08
    trinsic
    0.08
     inherent
    0.08
    é½IJåħ¨
    0.07
    æģ©æĸ¯
    0.07
    ×ķס
    0.07
    ãģĭãĤīãģł
    0.07
    Activations Density 0.294%

    No Known Activations