© 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. 18202
    Prev
    Next
    INDEX
    Explanations

    identifiers followed by numbers or symbols

    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±ķ
    -0.07
    ,
    -0.06
    /Users
    -0.06
    ucch
    -0.06
    ìĬ¤ëŁ¬
    -0.06
    ob
    -0.05
    ë§IJë¡ľ
    -0.05
    èĢĮä¸Ķæĺ¯
    -0.05
    ÙIJ
    -0.05
    çĪ±æĬ¤
    -0.05
    POSITIVE LOGITS
    ERTA
    0.10
    åħīæĺ¯
    0.09
    è«®
    0.08
    anax
    0.08
    ::$
    0.08
    人被
    0.08
    cpy
    0.08
    ergestellt
    0.07
    ä¼ļè®®åı¬å¼Ģ
    0.07
    º
    0.07
    Activations Density 0.006%

    No Known Activations