© 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. 59130
    Prev
    Next
    INDEX
    Explanations

    total volume

    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
    Negative Logits
    ×ķר×Ļ
    -0.08
    æĹ
    -0.07
    rix
    -0.07
    亿ä¸ĩ
    -0.07
    igem
    -0.07
    jem
    -0.07
    å·¨
    -0.06
    æĸī
    -0.06
     obv
    -0.06
    ì
    -0.06
    POSITIVE LOGITS
     total
    0.12
     overall
    0.11
    æĢ»
    0.11
    overall
    0.11
    total
    0.10
    æķ´ä½ĵçļĦ
    0.10
     Gesamt
    0.10
     insgesamt
    0.10
     totale
    0.10
    æķ´ä½ĵ
    0.10
    Activations Density 0.027%

    No Known Activations