© 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. 33380
    Prev
    Next
    INDEX
    Explanations

    aetiology

    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
    ä»Ĺ
    -0.07
    à¥į
    -0.07
    ogia
    -0.07
    ierer
    -0.06
    æīĽ
    -0.06
    à¥įà¤ŀ
    -0.06
    ìĿ´ìħĺ
    -0.06
    ়
    -0.06
    èĤĿçĤİ
    -0.06
    isées
    -0.06
    POSITIVE LOGITS
    oriously
    0.10
    koľ
    0.09
    ä¿±è¿Ľ
    0.08
    inander
    0.08
    adays
    0.08
    etheless
    0.08
    ì¤į
    0.07
    ìļ´ëį°
    0.07
    ãģ¡ãĤĥãĤĵãģ®
    0.07
    леÑģо
    0.07
    Activations Density 2.665%

    No Known Activations