© 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. 57699
    Prev
    Next
    INDEX
    Explanations

    define / definition

    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
    acs
    -0.07
    oven
    -0.07
    è°ģçŁ¥
    -0.06
    ihan
    -0.06
    recent
    -0.06
    fallen
    -0.06
    æĶĿ
    -0.06
    _css
    -0.06
    æijĦ
    -0.06
     emple
    -0.06
    POSITIVE LOGITS
    ableView
    0.08
    ëĶĶìĸ´
    0.08
    -extension
    0.08
     رÙĪÛĮ
    0.07
    -existent
    0.07
    è¿Ļ个åIJįåŃĹ
    0.07
    å¾·åŁº
    0.07
    楣
    0.07
    è¡¥ä¸ģ
    0.07
    Extension
    0.07
    Activations Density 0.014%

    No Known Activations