© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39355
    Prev
    Next
    INDEX
    Explanations

    legal proceedings or source material

    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
    Ä«j
    -0.07
    ÙĴرÙIJ
    -0.07
    æĪIJ为äºĨ
    -0.07
     bá»Ŀ
    -0.07
    аÑĤелÑĮÑģÑĤва
    -0.07
    repos
    -0.06
    ì²ł
    -0.06
    nett
    -0.06
     ifdef
    -0.06
    !:
    -0.06
    POSITIVE LOGITS
    ä¹ĭä¸Ģ
    0.08
    ä¸ĢåĪĩ
    0.07
    endet
    0.07
     iar
    0.07
    æīĭ足
    0.06
    足
    0.06
    ä¸ĢåŃĹ
    0.06
    instead
    0.06
    urr
    0.06
    umed
    0.06
    Activations Density 0.305%

    No Known Activations