© 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. 25796
    Prev
    Next
    INDEX
    Explanations

    arrows and separators

    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
    æµ·æ¶Ľ
    -0.07
    ma
    -0.07
    plex
    -0.07
    ç§ī
    -0.07
    pread
    -0.07
    rus
    -0.07
    yai
    -0.07
    ry
    -0.07
    ÙĦÙĬ
    -0.07
    ëģ¼
    -0.06
    POSITIVE LOGITS
     ÑģобÑģÑĤвенно
    0.08
    âĢ¦âĢ¦ãĢĤ
    0.07
     enfin
    0.07
    åĥıä½ł
    0.07
    (optional
    0.07
    -done
    0.07
    ä¾Ŀ次为
    0.07
    åıĪæĺ¯ä¸Ģå¹´
    0.07
     Ñģнова
    0.07
     schlieÃŁlich
    0.06
    Activations Density 0.059%

    No Known Activations