© 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. 37437
    Prev
    Next
    INDEX
    Explanations

    tertiary compounds

    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
    ../
    -0.10
    ziger
    -0.09
    ings
    -0.09
    å¾Ĺèµ·
    -0.08
    bject
    -0.08
    è¿Ļè¿ĺæĺ¯
    -0.08
    heets
    -0.08
    cean
    -0.08
    è¶Ł
    -0.07
    åħĭç¦ı
    -0.07
    POSITIVE LOGITS
    ity
    0.09
    ĸ
    0.08
    ois
    0.07
    ális
    0.07
    allis
    0.07
    -vars
    0.07
    بط
    0.07
    avig
    0.07
    witter
    0.06
    emen
    0.06
    Activations Density 0.003%

    No Known Activations