© 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. 28378
    Prev
    Next
    INDEX
    Explanations

    cases and situations

    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
    èĻ½çĦ¶ä»ĸ
    -0.07
    kans
    -0.07
    reif
    -0.07
    atern
    -0.06
    acan
    -0.06
    èĻ½çĦ¶
    -0.06
    èĻ½çĦ¶çİ°åľ¨
    -0.06
    èĻ½å°ı
    -0.06
    .Generated
    -0.06
    ubar
    -0.06
    POSITIVE LOGITS
     cases
    0.10
    Cases
    0.09
    ä¸įåIJĮç±»åŀĭçļĦ
    0.09
    otherwise
    0.09
    _cases
    0.09
     Fälle
    0.08
    ãģ®åł´åIJĪ
    0.08
     Cases
    0.08
     situations
    0.08
    çŃīæĥħåĨµ
    0.08
    Activations Density 0.108%

    No Known Activations