© 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. 10095
    Prev
    Next
    INDEX
    Explanations

    all real zeros

    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
    ild
    -0.07
    aci
    -0.07
     Trem
    -0.06
    velle
    -0.06
    ijo
    -0.06
    മാ
    -0.06
    enciales
    -0.06
    çļĦæĹ¥å¸¸
    -0.06
    ola
    -0.06
    ela
    -0.06
    POSITIVE LOGITS
    mehr
    0.07
    /assert
    0.07
    éĵ
    0.07
    æŶéļĶ
    0.07
    fone
    0.07
    æī
    0.07
    sgi
    0.07
    wany
    0.07
    entino
    0.06
    ↵↵    ↵
    0.06
    Activations Density 0.032%

    No Known Activations