© 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. 1462
    Prev
    Next
    INDEX
    Explanations

    other than

    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
    çIJ
    -0.10
    两大
    -0.07
    å·²ç»ı
    -0.07
    两项
    -0.06
    就已ç»ı
    -0.06
    åħ©å¤§
    -0.06
    vc
    -0.06
    就已
    -0.06
    è¿Ļ两ç§į
    -0.06
     Pass
    -0.06
    POSITIVE LOGITS
     similarly
    0.12
    类似çļĦ
    0.11
    类似éĹ®é¢ĺ
    0.11
    åIJĮçIJĨ
    0.10
     ìĿ´ì²ĺëŁ¼
    0.10
     подобнÑĭÑħ
    0.10
    类似
    0.10
    similar
    0.10
    æĢ»ä¹ĭ
    0.09
     nữa
    0.09
    Activations Density 0.210%

    No Known Activations