© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 43787
    Prev
    Next
    INDEX
    Explanations

    intersection of

    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
    Not in Any Lists

    No Comments

    Negative Logits
    rael
    -0.07
    åıĺåĮĸæĥħåĨµ
    -0.06
    èĩªçŁ¥
    -0.06
    ×ķ×ĸ
    -0.06
    others
    -0.06
     Reuters
    -0.06
    çŁ¥éģĵèĩªå·±çļĦ
    -0.06
     replacements
    -0.06
    riel
    -0.06
    åĥıä¸Ģåıª
    -0.06
    POSITIVE LOGITS
     intersect
    0.10
     intersection
    0.10
    Intersection
    0.09
     Intersection
    0.09
    intersection
    0.08
     intersections
    0.08
    äºĮèĢħ
    0.08
    ç»ĵåIJĪ
    0.08
    两èĢħ
    0.08
    交éĽĨ
    0.08
    Activations Density 0.273%

    No Known Activations