© 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. 20207
    Prev
    Next
    INDEX
    Explanations

    both or all

    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
    çļĦæīĢæľī
    -0.10
    ë§ĪìŀIJ
    -0.09
     ÙĥÙĦÙĩ
    -0.09
     nÃło
    -0.09
     altogether
    -0.08
    ä¸ŃçļĦæīĢæľī
    -0.08
     justru
    -0.08
    ç§įç§į
    -0.08
    udit
    -0.08
    æīĢæľīåĨħ容
    -0.08
    POSITIVE LOGITS
     Äijặn
    0.22
    æĪĸéĥ¨åĪĨ
    0.08
    éģĵåºľ
    0.08
    ä¸įåIJĮç¨ĭ度çļĦ
    0.08
    EMENT
    0.08
    rary
    0.07
    ä¸įåIJĮç¨ĭ度
    0.07
    ergic
    0.07
     sortes
    0.07
    minated
    0.07
    Activations Density 0.007%

    No Known Activations