© 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. 21523
    Prev
    Next
    INDEX
    Explanations

    first, MRI, follow, they, movement, 1, The, Pr, holiday

    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
    å¸Ń
    -0.08
    atcher
    -0.08
    isphere
    -0.08
    ÃŃna
    -0.08
     @}
    -0.07
    epad
    -0.07
    ersi
    -0.07
    个人页
    -0.07
    åİ®
    -0.07
    ĮĢ
    -0.07
    POSITIVE LOGITS
    ä¸Ģ
    0.09
     Basics
    0.09
     firstly
    0.08
    <h
    0.07
    æ¦Ĥè¿°
    0.07
    defs
    0.07
    æŃ£æĸĩ
    0.07
     Ø£ÙĪÙĦاÙĭ
    0.07
    åĬłå¼ºåŃ¦ä¹ł
    0.07
    ç¼ĺ
    0.07
    Activations Density 1.397%

    No Known Activations