© 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. 35049
    Prev
    Next
    INDEX
    Explanations

    command to run

    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
    æ¸IJæ¸IJ
    -0.07
    igo
    -0.07
     Grad
    -0.07
     gradually
    -0.06
    าร
    -0.06
    fit
    -0.06
    度è¿ĩ
    -0.06
    haf
    -0.06
     Har
    -0.06
    å¹´åĨħ
    -0.06
    POSITIVE LOGITS
    utum
    0.09
    ä¹ĭåIJİçļĦ
    0.08
    ÃŁer
    0.08
    oke
    0.08
    æĽ´å¤ļåĽŀçŃĶ
    0.08
    ستÛĮ
    0.08
    adet
    0.08
    _LOOK
    0.07
    _touch
    0.07
    egers
    0.07
    Activations Density 0.018%

    No Known Activations