© 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. 30351
    Prev
    Next
    INDEX
    Explanations

    y in expressions

    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
    MB
    -0.07
    Wo
    -0.07
    åİŁåĪĻä¸Ĭ
    -0.07
    çļĦéħįåIJĪ
    -0.06
    åĮħ
    -0.06
    åŃĺ
    -0.06
    éħįåIJĪ
    -0.06
    åıªè§ģ
    -0.06
    é¦ĸåħĪæĺ¯
    -0.06
    G
    -0.06
    POSITIVE LOGITS
    ä½łè¿ĺåı¯ä»¥
    0.09
    ä½łä¹Łåı¯ä»¥
    0.08
    istream
    0.08
    HeaderText
    0.08
    ĻĤ
    0.08
    ÑĤеÑĢна
    0.08
    utas
    0.08
    iett
    0.08
     Coup
    0.08
    ayment
    0.07
    Activations Density 0.001%

    No Known Activations