© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16268
    Prev
    Next
    INDEX
    Explanations

    connect, database, helper, cookie

    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
    éģĵåıĭ
    -0.07
    eken
    -0.07
    ç½ijç«Ļå¤ĩæ¡Ī
    -0.07
    essler
    -0.07
    ä¸įæĮ¯
    -0.07
    yat
    -0.06
    عات
    -0.06
    åºĶå½ĵæĮīçħ§
    -0.06
    .dumps
    -0.06
    åIJĮ士
    -0.06
    POSITIVE LOGITS
    ngine
    0.08
    ILLE
    0.08
    临
    0.08
    ä¾Ľå¤§å®¶åıĤèĢĥ
    0.07
    æīĢåľ¨ä½įç½®
    0.07
    inata
    0.07
    endr
    0.07
    enburg
    0.07
    _dev
    0.07
    çal
    0.07
    Activations Density 0.001%

    No Known Activations