© 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. 47886
    Prev
    Next
    INDEX
    Explanations

    tools and supplies

    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
     boo
    -0.08
     principal
    -0.08
    ellan
    -0.07
    çĽ¸æľĽ
    -0.07
    ä¸įçŁ¥éģĵèĩªå·±
    -0.07
     hopeful
    -0.07
    sembl
    -0.07
     tenure
    -0.07
    issen
    -0.06
     quasi
    -0.06
    POSITIVE LOGITS
    vsp
    0.08
    cpy
    0.08
    /tiny
    0.07
    æĹłå¿Į
    0.07
    OCK
    0.07
    çļĦæľĭåıĭåı¯ä»¥
    0.07
    å»ºåĽ½
    0.07
    nul
    0.07
    utility
    0.07
    INY
    0.07
    Activations Density 0.055%

    No Known Activations