© 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. 9266
    Prev
    Next
    INDEX
    Explanations

    van der Waals dispersion forces

    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
    .isOpen
    -0.07
    ÑĢино
    -0.07
    ebin
    -0.07
    æĸ©
    -0.07
    abus
    -0.07
    饶
    -0.07
    ylv
    -0.07
    #
    -0.07
    abet
    -0.07
    lemn
    -0.07
    POSITIVE LOGITS
    åģ¶
    0.08
    åIJ¸å°ĺ
    0.08
    åı¯è¨Ģ
    0.07
    å¡ļ
    0.07
    Ã¶ÃŁe
    0.07
    É
    0.07
     thôi
    0.07
    ÙİاÙĩ
    0.07
    åľ°çĽ¯çĿĢ
    0.07
    getAll
    0.07
    Activations Density 0.002%

    No Known Activations