© 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. 34291
    Prev
    Next
    INDEX
    Explanations

    units and concentrations in solutions

    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
     Bale
    -0.07
    ignan
    -0.07
    à¸Ĺ
    -0.07
     Jaya
    -0.07
    liest
    -0.07
    ä¸įèĥľ
    -0.07
    stantiate
    -0.07
    ä»ĺåĩº
    -0.07
    antan
    -0.07
     ssize
    -0.07
    POSITIVE LOGITS
    ä¸įåıĤåĬł
    0.08
    伯ä¹IJ
    0.07
    optional
    0.07
     ekstra
    0.07
    æIJħ
    0.07
     optional
    0.07
     except
    0.07
    éģ¿
    0.07
    æµĵ度为
    0.07
    enz
    0.06
    Activations Density 0.088%

    No Known Activations