© 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. 571
    Prev
    Next
    INDEX
    Explanations

    medical conditions and treatments

    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
     mute
    -0.07
    以轻
    -0.07
     Meh
    -0.07
    ç»ıæµİæĬĢæľ¯
    -0.07
    ợ
    -0.06
    ĤŃ
    -0.06
    кономи
    -0.06
    ahn
    -0.06
    linger
    -0.06
     Dere
    -0.06
    POSITIVE LOGITS
    åı¯ä»¥èĩªå·±
    0.13
    either
    0.13
     either
    0.13
    è¦ģä¹Īæĺ¯
    0.13
    æĪij们èĩªå·±
    0.12
    éĥ½æĺ¯èĩªå·±
    0.12
     externally
    0.12
    èĩªè¡Į
    0.11
    人为
    0.11
    è¦ģä¹Ī
    0.11
    Activations Density 0.623%

    No Known Activations