© 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. 25248
    Prev
    Next
    INDEX
    Explanations

    assignment of boolean or none

    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
    ansk
    -0.07
    æ±Łè·¯
    -0.07
    对åħ¶
    -0.06
    对åħ¶è¿Ľè¡Į
    -0.06
     fac
    -0.06
    æĤī
    -0.06
    .toBe
    -0.06
    .Annotation
    -0.06
    acher
    -0.06
    åIJĮæ¯Ķåĩıå°ij
    -0.06
    POSITIVE LOGITS
    èĢ¿èĢ¿
    0.08
    oje
    0.08
    ¬´
    0.08
     azért
    0.08
    à¸ģะ
    0.08
    houd
    0.08
    æĤ¨çļĦè¯Ħ论
    0.08
    åľ¨åįĬ
    0.08
    大åı¯
    0.07
    _basename
    0.07
    Activations Density 0.021%

    No Known Activations