© 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. 61318
    Prev
    Next
    INDEX
    Explanations

    4

    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
    _processors
    -0.08
    æĺİå¹´
    -0.08
    hamster
    -0.07
    ...**
    -0.07
    á»ĵn
    -0.07
    á»ĵm
    -0.07
     Patt
    -0.07
    onso
    -0.07
    "],["
    -0.07
    ä¸ľè·¯
    -0.07
    POSITIVE LOGITS
    çŀİ
    0.07
    ulté
    0.06
     sig
    0.06
    äºĨä¸Ģå¥Ĺ
    0.06
    istica
    0.06
    ann
    0.06
    éĢļè¿ĩåľ¨
    0.06
    seealso
    0.06
    -Smith
    0.06
    áĢľáĢŃáĢ¯
    0.06
    Activations Density 0.061%

    No Known Activations