© 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. 14810
    Prev
    Next
    INDEX
    Explanations

    works, fine, okay, or re-elected

    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
    æ§Ľ
    -0.07
    çĿIJ
    -0.07
    åħ·æľī以ä¸ĭ
    -0.07
    æĽ´ä¸º
    -0.07
    psilon
    -0.07
    à¦ĺ
    -0.07
    並ä¸į
    -0.07
    combined
    -0.07
    并没
    -0.06
    reven
    -0.06
    POSITIVE LOGITS
    äºĨåIJ§
    0.07
    人å¤ļ
    0.07
    çļĦå°±æĺ¯
    0.06
    witz
    0.06
    inent
    0.06
    åIJĮä¸Ĭ
    0.06
    -ish
    0.06
    æ¢Ń
    0.06
    опо
    0.06
    änk
    0.06
    Activations Density 0.011%

    No Known Activations