© 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. 28974
    Prev
    Next
    INDEX
    Explanations

    natural phenomena and elements

    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
    номо
    -0.08
    lard
    -0.07
    nton
    -0.06
    转åıĺ
    -0.06
    åīįæīĢæľª
    -0.06
    aments
    -0.06
    Ãłng
    -0.06
    æĬĺä¸įæī£
    -0.06
    PROC
    -0.06
    -addons
    -0.06
    POSITIVE LOGITS
    è§ģè¯ģäºĨ
    0.08
    è¿ĻäºĽåĽłç´ł
    0.08
     altında
    0.07
    å®ŀéªĮåŃ¦æł¡
    0.07
     baise
    0.07
    书é¦Ļ
    0.07
    èĪ¬çļĦ
    0.07
    hoch
    0.07
    ä¸Ģåį·
    0.07
    ainted
    0.07
    Activations Density 0.038%

    No Known Activations