© 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. 7035
    Prev
    Next
    INDEX
    Explanations

    Catch as Catch Can

    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
    åĪ°åĵªéĩĮ
    -0.08
    agy
    -0.07
    ól
    -0.07
    ä¸Ńå¿ĥåĴĮ
    -0.06
    óż
    -0.06
    Ĵáŀ
    -0.06
    ÃŃÅ¡
    -0.06
     Stam
    -0.06
     optimism
    -0.06
    æĢ»æľī
    -0.06
    POSITIVE LOGITS
    acte
    0.07
    ä¹Ķ
    0.06
    åıįéĹ®
    0.06
    tez
    0.06
    .fm
    0.06
    çªį
    0.06
     fart
    0.06
    _SCHED
    0.06
    wort
    0.06
    èĩªæĭĶ
    0.06
    Activations Density 0.001%

    No Known Activations