© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34795
    Prev
    Next
    INDEX
    Explanations

    code, numbers, and punctuation

    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
    е
    -0.07
    éĺ´éĺ³
    -0.06
     Boul
    -0.06
    enha
    -0.06
    Cr
    -0.06
    um
    -0.06
    ä¹ĭæľ¬
    -0.06
    æ¯Ľ
    -0.06
    ÙĦس
    -0.06
    ome
    -0.06
    POSITIVE LOGITS
    adrat
    0.08
    pio
    0.08
    byss
    0.08
    endem
    0.08
    ìĭłë¬¸
    0.08
     référenc
    0.07
    undur
    0.07
    ayscale
    0.07
    çłģ
    0.07
    дай
    0.07
    Activations Density 0.026%

    No Known Activations