© 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. 16634
    Prev
    Next
    INDEX
    Explanations

    colors and game features

    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
    iece
    -0.10
    oucher
    -0.08
    æľīæīĢæĢĿ
    -0.08
    å¼łæĸĩ
    -0.07
    CHAIN
    -0.07
     pin
    -0.07
     paced
    -0.07
    伸åĩºæīĭ
    -0.07
    ulum
    -0.06
    sembled
    -0.06
    POSITIVE LOGITS
    (default
    0.09
    éĢļçĶ¨
    0.08
    æĿ¡
    0.08
    常éĩı
    0.07
    -color
    0.07
    ä¸Ģæĸ¹
    0.07
    Distinct
    0.07
    aleb
    0.07
    åĩ¡
    0.07
    éĢļ
    0.07
    Activations Density 0.008%

    No Known Activations