© 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. 790
    Prev
    Next
    INDEX
    Explanations

    opioids and tachykinins

    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
    .nodeType
    -0.08
    igan
    -0.07
    mun
    -0.07
    erto
    -0.07
    ä¿¡æģ¯åĴĮ
    -0.07
    åħ¶æīĢ
    -0.07
    orama
    -0.07
    áĥĿáĥĵ
    -0.07
    ighton
    -0.07
    uffy
    -0.07
    POSITIVE LOGITS
    们
    0.09
    ä¹ĭä¸ĢçļĦ
    0.09
    åĴĮ西
    0.08
    ä»¬åľ¨
    0.08
    åĢij
    0.08
    ç±»èį¯çī©
    0.08
    like
    0.08
    aceous
    0.07
    家æĹıçļĦ
    0.07
    ų
    0.07
    Activations Density 0.298%

    No Known Activations