© 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. 60539
    Prev
    Next
    INDEX
    Explanations

    alternative options or comparisons

    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
    imonial
    -0.07
     unc
    -0.07
    ingleton
    -0.07
    owell
    -0.07
    ethoven
    -0.07
     equ
    -0.06
    atural
    -0.06
    plevel
    -0.06
    ئÙĥ
    -0.06
    elight
    -0.06
    POSITIVE LOGITS
    лак
    0.07
    大éĥ¨ä»½
    0.07
    ouer
    0.07
    åĩºå¥ĩ
    0.07
    å«©çļĦ
    0.06
    fei
    0.06
    ä¸ĭæ°´
    0.06
    xDA
    0.06
    enzio
    0.06
     resumes
    0.06
    Activations Density 1.294%

    No Known Activations