© 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. 34301
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and nature

    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
    imbus
    -0.09
    hte
    -0.09
    à¸ĩาม
    -0.09
    itage
    -0.08
    issance
    -0.08
    hares
    -0.08
    ÏĢοÏĦε
    -0.08
    osz
    -0.08
    好å¤ĦçļĦ
    -0.08
    æĸĽ
    -0.08
    POSITIVE LOGITS
    o
    0.10
    ation
    0.09
    ness
    0.08
    s
    0.08
    ively
    0.08
    -minded
    0.08
    Ùĩ
    0.08
    ed
    0.07
    ä¸įæ¸ħ
    0.07
    ly
    0.07
    Activations Density 0.021%

    No Known Activations