© 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. 43880
    Prev
    Next
    INDEX
    Explanations

    code snippet or section

    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
    èĽ®
    -0.06
    ))->
    -0.06
    èİ«éĿŀ
    -0.06
    丽
    -0.06
    endis
    -0.06
    Vict
    -0.06
    “
    -0.06
    诸èijĽ
    -0.06
    ä¸ĺ
    -0.06
    ÙĬاز
    -0.06
    POSITIVE LOGITS
    以åıĬåľ¨
    0.10
     saja
    0.10
     lisäksi
    0.10
     disertai
    0.08
    estiv
    0.08
    èĭ±æĸĩåIJįåŃĹ
    0.08
    åį³åı¯
    0.08
     beserta
    0.08
    åį³åı¯å®ĮæĪIJ
    0.08
    æĢ§ä»¥åıĬ
    0.08
    Activations Density 0.005%

    No Known Activations