© 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. 44423
    Prev
    Next
    INDEX
    Explanations

    ten-year

    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
    зÑĮ
    -0.08
    utto
    -0.08
    igham
    -0.08
    ê¹IJ
    -0.08
    tes
    -0.07
    inq
    -0.07
    دÙĬÙĨ
    -0.07
    andler
    -0.07
    полне
    -0.07
    HING
    -0.07
    POSITIVE LOGITS
    antry
    0.10
    OrCreate
    0.08
    auan
    0.08
     Downing
    0.08
    burgh
    0.07
    ì°©
    0.07
    ahoma
    0.07
    å°¼æĸ¯
    0.07
    GMEM
    0.07
    mund
    0.07
    Activations Density 0.315%

    No Known Activations