© 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. 42753
    Prev
    Next
    INDEX
    Explanations

    above or below

    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
    ekan
    -0.07
    æĭ¶
    -0.07
    種ãģ®
    -0.07
     alike
    -0.07
    زÙĦ
    -0.07
    rought
    -0.07
    trys
    -0.07
    ÙĬÙĨØ©
    -0.07
    åĿĩæĿ¥èĩª
    -0.07
    eturn
    -0.07
    POSITIVE LOGITS
    æĭīå¾·
    0.08
    :\/\/
    0.07
    ä¸ĬéĻIJ
    0.07
    iki
    0.07
     limit
    0.07
    HEET
    0.07
    ä¸ĭéĻIJ
    0.07
     interval
    0.06
     limite
    0.06
    веÑĢи
    0.06
    Activations Density 0.009%

    No Known Activations