© 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. 58684
    Prev
    Next
    INDEX
    Explanations

    existence of

    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
    imately
    -0.08
    bland
    -0.07
    quanto
    -0.07
    missive
    -0.07
     theirs
    -0.07
    jure
    -0.07
     ours
    -0.07
    ters
    -0.07
    éĿ¢çĽ¸
    -0.07
    è¯Ŀ
    -0.07
    POSITIVE LOGITS
    ä¸İåIJ¦
    0.08
    ilah
    0.08
    åŃĺåľ¨
    0.08
    /use
    0.07
    iller
    0.07
    è¿Ļæł·ä¸Ģ个
    0.07
    è¿Ļä¹Īä¸Ģ个
    0.07
    涯
    0.07
    SKIP
    0.07
    åŃĺåľ¨çĿĢ
    0.07
    Activations Density 0.132%

    No Known Activations