© 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. 49792
    Prev
    Next
    INDEX
    Explanations

    single case studies

    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
    æĺ¯ä¸Ģ群
    -0.09
    orer
    -0.08
    åıĮåıĮ
    -0.08
    .querySelectorAll
    -0.08
    è¿Ļ两ä½į
    -0.07
    æµ
    -0.07
    æ¯ıå¼ł
    -0.07
    æı
    -0.07
    xCD
    -0.07
    é¦ĸæī¹
    -0.07
    POSITIVE LOGITS
    åįķä¸Ģ
    0.15
    åįķä¸ĢçļĦ
    0.14
     single
    0.14
    åıªæľīä¸Ģ个
    0.14
    .single
    0.13
     Single
    0.12
    single
    0.12
    Single
    0.12
    SingleNode
    0.11
    åĸ®ä¸Ģ
    0.11
    Activations Density 0.431%

    No Known Activations