© 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. 45480
    Prev
    Next
    INDEX
    Explanations

    Microsoft products

    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
    çijŀæĭī
    -0.09
    ftime
    -0.08
    çª
    -0.08
    åŃIJéĩĮ
    -0.08
    utra
    -0.08
    ajak
    -0.08
    гда
    -0.08
    odb
    -0.08
    /she
    -0.08
    oreign
    -0.08
    POSITIVE LOGITS
     Arabia
    0.08
    's
    0.07
    auer
    0.07
    uplic
    0.06
    -backed
    0.06
    ä¸İåIJĦ
    0.06
    åħ¨ç¾İ
    0.06
    çŀ©çĽ®
    0.06
    åĴĮç¾İåĽ½
    0.06
    anian
    0.06
    Activations Density 0.225%

    No Known Activations