© 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. 55139
    Prev
    Next
    INDEX
    Explanations

    exact, novelty, copyrighted, matching

    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
     conse
    -0.07
    ิยม
    -0.07
    島
    -0.07
     omin
    -0.06
    abouts
    -0.06
    è½®æµģ
    -0.06
    è½®çķª
    -0.06
    èĩªçĦ¶çķĮ
    -0.06
    itzt
    -0.06
     porad
    -0.06
    POSITIVE LOGITS
    åĮ¹éħį
    0.12
     mismatch
    0.12
     match
    0.12
     matching
    0.10
    .matches
    0.10
     mism
    0.10
     ÑģооÑĤвеÑĤÑģÑĤвие
    0.10
    match
    0.10
    æ¯Ķ对
    0.09
     Match
    0.09
    Activations Density 0.005%

    No Known Activations