© 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. 39060
    Prev
    Next
    INDEX
    Explanations

    of course

    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
    ЧÐĺ
    -0.09
    insky
    -0.08
    ategorized
    -0.08
    abar
    -0.07
    ãĤŃãĤ·
    -0.07
    éĿŀ常æĺİæĺ¾
    -0.07
    еÑģо
    -0.07
     Bail
    -0.07
    èµ°åIJijä¸ĸçķĮ
    -0.07
    apel
    -0.07
    POSITIVE LOGITS
     подÑĢазÑĥмеваеÑĤ
    0.07
     likely
    0.07
    uar
    0.07
    à¹Ģà¸Ħร
    0.07
    åĬłæĭ¿å¤§
    0.07
     perhaps
    0.07
    æĸ°åĬłåĿ¡
    0.07
    å¼Ģåħ³çĶµæºIJ
    0.07
     presumably
    0.07
    ëħIJ
    0.07
    Activations Density 0.001%

    No Known Activations