© 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. 35013
    Prev
    Next
    INDEX
    Explanations

    numeric parts of diffs

    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
    伦
    -0.08
    XObject
    -0.07
    伦å¤ļ
    -0.07
    ÙİÙijÙī
    -0.07
    éĺ²
    -0.06
     ideas
    -0.06
    å°ĸ
    -0.06
    én
    -0.06
    è¿ľè¿ľçļĦ
    -0.06
    温åĴĮ
    -0.06
    POSITIVE LOGITS
    bish
    0.08
    trup
    0.07
    eline
    0.07
    ä¹ĭ家
    0.07
    ël
    0.07
    zel
    0.07
    oki
    0.07
    eah
    0.07
    rett
    0.07
    xBF
    0.07
    Activations Density 0.001%

    No Known Activations