© 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. 31910
    Prev
    Next
    INDEX
    Explanations

    code snippet or example

    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
    agio
    -0.08
    çīµ
    -0.08
    诸
    -0.07
    åħ³äºİ
    -0.07
    éĢļè¿ĩ对
    -0.07
    离
    -0.07
     "/",
    -0.07
    æı¡
    -0.06
    æľīåĪ©äºİ
    -0.06
    ä¹Ŀ游
    -0.06
    POSITIVE LOGITS
    为天
    0.08
    æĸ¹éĿ¢çļĦéĹ®é¢ĺ
    0.08
    icker
    0.08
     Raya
    0.08
     snippet
    0.08
    Snippet
    0.07
    å®ŀéĻħçļĦ
    0.07
     ver
    0.07
     demonstr
    0.07
     snippets
    0.07
    Activations Density 0.044%

    No Known Activations