© 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. 37645
    Prev
    Next
    INDEX
    Explanations

    physics groups

    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
    ĮĢ
    -0.08
    aku
    -0.07
    èīĩ
    -0.07
     Lime
    -0.07
    spm
    -0.07
    ibat
    -0.06
     Drum
    -0.06
     drum
    -0.06
    è°¢ç»Ŀ
    -0.06
    ULO
    -0.06
    POSITIVE LOGITS
    agli
    0.08
    incs
    0.08
    templ
    0.07
    ooks
    0.07
     nami
    0.07
    tev
    0.07
    ÏħÏĩ
    0.07
    oir
    0.07
    ütt
    0.07
    æ¶ĪåĮĸåIJ¸æĶ¶
    0.07
    Activations Density 0.002%

    No Known Activations