© 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. 25985
    Prev
    Next
    INDEX
    Explanations

    arrangement and comparison

    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
    Ø®ÙĬ
    -0.08
    ombe
    -0.08
    oeff
    -0.08
    rensa
    -0.07
    engeb
    -0.07
    ä¸įåı¯éģ¿åħįåľ°
    -0.07
    atte
    -0.07
    æįħ
    -0.07
    ä¹ŁçŁ¥éģĵ
    -0.07
    fy
    -0.07
    POSITIVE LOGITS
     similarities
    0.09
    åIJĮ为
    0.08
     grouping
    0.08
    çĽ¸ä¼¼çļĦ
    0.07
    æĺ¯åIJĮ
    0.07
     differing
    0.07
    -groups
    0.07
    åIJĮç±»
    0.07
    大家éĥ½æĺ¯
    0.07
    -group
    0.07
    Activations Density 0.002%

    No Known Activations