© 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. 12533
    Prev
    Next
    INDEX
    Explanations

    mathematical equations with exponents

    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
    axed
    -0.06
    eba
    -0.05
    çľĭæĬ¤
    -0.05
    å¾ĴæŃ©
    -0.05
    ä¸Ģè§ģ
    -0.05
    ãģ£ãģĵ
    -0.05
    ins
    -0.05
    ame
    -0.05
    èĢIJå¿ĥ
    -0.05
    顯
    -0.05
    POSITIVE LOGITS
    ergeb
    0.08
    @if
    0.07
    .equ
    0.07
    åľ¨çº¿éĺħ读
    0.07
    inggu
    0.07
    夫
    0.07
    terior
    0.07
    Ä«bÄģ
    0.07
    æĸĽ
    0.07
    esso
    0.07
    Activations Density 0.022%

    No Known Activations