© 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. 33930
    Prev
    Next
    INDEX
    Explanations

    objects and their properties

    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
     zet
    -0.07
    æĦıä¹īä¸ĬçļĦ
    -0.06
    èĩªå·±çļĦ缮æłĩ
    -0.06
    alore
    -0.06
    ags
    -0.06
    çĬ¶çļĦ
    -0.06
    Ø©
    -0.06
    IndexOf
    -0.06
     tro
    -0.06
     versa
    -0.06
    POSITIVE LOGITS
    æĿŀ
    0.08
    客座
    0.08
    æĿ¥æºIJç½ij绾
    0.08
    culos
    0.08
    ropp
    0.07
    rott
    0.07
    benh
    0.07
    ิà¸ĩ
    0.07
    ä¸»å¯¼åľ°ä½į
    0.07
    å°±æĢķ
    0.07
    Activations Density 0.050%

    No Known Activations