© 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. 52170
    Prev
    Next
    INDEX
    Explanations

    field, square root, cubic extension

    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
    æĹłçĥŁ
    -0.07
     Ñĥго
    -0.07
    ockey
    -0.07
     EITHER
    -0.07
    åĴ«
    -0.07
    faits
    -0.07
    Ñĸз
    -0.06
    /models
    -0.06
    èĵī
    -0.06
    stel
    -0.06
    POSITIVE LOGITS
    Splash
    0.09
     Splash
    0.08
    линг
    0.08
    avenport
    0.08
     splash
    0.07
    valu
    0.07
    æijĶ
    0.07
    spl
    0.07
    æ°´ä½į
    0.07
    ãĥīãĥŃ
    0.07
    Activations Density 0.004%

    No Known Activations