© 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. 59091
    Prev
    Next
    INDEX
    Explanations

    sha256 hash values

    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
    _dispatcher
    -0.08
    Dispatcher
    -0.08
    áĥ¥
    -0.07
    æ´Ĺ礼
    -0.07
    å¥Ĺ
    -0.07
     incon
    -0.07
     dispens
    -0.06
    opedia
    -0.06
    mob
    -0.06
     ostr
    -0.06
    POSITIVE LOGITS
    ahari
    0.08
    çĻ½æĹ¥
    0.07
    佼佼
    0.07
     (()
    0.07
     keyCode
    0.07
    onti
    0.07
    δη
    0.07
    æľ¬å±Ĭ
    0.07
    ogene
    0.07
     sourced
    0.07
    Activations Density 0.001%

    No Known Activations