© 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. 10012
    Prev
    Next
    INDEX
    Explanations

    indexed variables

    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
    ÙĥÙĪÙħ
    -0.08
    عاÙħ
    -0.07
    ä¹IJçļĦ
    -0.07
    _requires
    -0.07
    ://${
    -0.07
    两èĢħçļĦ
    -0.07
    éĹº
    -0.06
    èĢĮåIJĮ
    -0.06
     bùn
    -0.06
    ductive
    -0.06
    POSITIVE LOGITS
    éļ
    0.08
    éļ¶å±ŀäºİ
    0.08
     à¹Ĩ
    0.08
    ç¡·
    0.08
    ç¼ĸåı·
    0.07
    建平
    0.07
     j
    0.07
     blockIdx
    0.07
    linky
    0.07
    érc
    0.07
    Activations Density 0.010%

    No Known Activations