© 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. 10125
    Prev
    Next
    INDEX
    Explanations

    alpha, H, CG

    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
    res
    -0.07
    大æľī
    -0.07
    expects
    -0.06
    çªģçł´äºĨ
    -0.06
    coni
    -0.06
     ανά
    -0.06
    æķ´
    -0.06
     i
    -0.06
    è´¨çļĦ
    -0.06
    anner
    -0.06
    POSITIVE LOGITS
     Prospect
    0.08
    æ³Ĺ
    0.08
    adeira
    0.08
    Smarty
    0.08
    uhe
    0.08
    spect
    0.08
    á»ķng
    0.08
    trup
    0.07
    à¥Ĥस
    0.07
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    0.07
    Activations Density 0.341%

    No Known Activations