© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12077
    Prev
    Next
    INDEX
    Explanations

    explanation, story, difference, patients, newsletter

    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
    è¨Ģéģĵ
    -0.07
    oret
    -0.06
    owitz
    -0.06
    çŃīåIJĦç§į
    -0.06
    æĤ¨çļĦéĹ®é¢ĺ
    -0.06
    缴æİ¥æĪĸ
    -0.06
    ersey
    -0.06
     Pes
    -0.06
    _argument
    -0.06
    çŃīä¼Ĺå¤ļ
    -0.06
    POSITIVE LOGITS
    æĥħåĨµè¯´æĺİ
    0.08
    æľīåij³
    0.08
    "--
    0.08
     detailing
    0.07
    "%
    0.07
    =!
    0.07
    æĺİäºĨ
    0.07
    ÙĪضØŃ
    0.07
     copp
    0.07
    &q
    0.07
    Activations Density 0.007%

    No Known Activations