© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30566
    Prev
    Next
    INDEX
    Explanations

    plist xml structures

    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
    éĶ¥
    -0.08
    åĸĿçĿĢ
    -0.07
     Maver
    -0.07
    uan
    -0.06
     vig
    -0.06
     Sez
    -0.06
     integra
    -0.06
     Manning
    -0.06
    符åı·
    -0.06
    åīįæľī
    -0.06
    POSITIVE LOGITS
    uschen
    0.08
    å·¥ç¨ĭéĻ¢
    0.08
    æĹ©çŁ¥éģĵ
    0.08
    culares
    0.08
    esser
    0.08
    hamn
    0.08
    à§įষ
    0.08
    解çŃĶ
    0.08
    ÙĦÙĬÙħ
    0.08
    iesel
    0.07
    Activations Density 0.001%

    No Known Activations