© 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. 4754
    Prev
    Next
    INDEX
    Explanations

    medic_patient, urinary tract

    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
    åħ¨éĿ¢åĬłå¼º
    -0.08
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    -0.07
    tap
    -0.07
     thrift
    -0.07
    åıĭ
    -0.07
    jac
    -0.06
    _wh
    -0.06
     stylist
    -0.06
    aring
    -0.06
    istre
    -0.06
    POSITIVE LOGITS
    å®ĥä¸İ
    0.16
     combination
    0.15
     pairing
    0.15
    åı¯ä»¥ä¸İ
    0.15
     paired
    0.14
    è¦ģä¸İ
    0.14
    æIJŃéħį
    0.14
    åħ¶ä¸İ
    0.14
    并ä¸İ
    0.14
    åºĶä¸İ
    0.14
    Activations Density 0.516%

    No Known Activations