© 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. 11994
    Prev
    Next
    INDEX
    Explanations

    .h files, CTest, Graphics, Store

    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
    Touches
    -0.08
    ummies
    -0.08
    olds
    -0.08
    ptive
    -0.07
    åĬĽå£«
    -0.07
    åĪºå®¢
    -0.07
     bothering
    -0.07
    Enumerator
    -0.07
    ensus
    -0.07
    ä¸İçݯå¢ĥ
    -0.06
    POSITIVE LOGITS
    ihan
    0.07
    éĤ£æĿ¡
    0.07
    æŁı
    0.07
    æīĢåĪĹ
    0.07
    毫ä¸įçĬ¹è±«
    0.06
    èĹ©
    0.06
    两ä¼ļ
    0.06
    èĦ³
    0.06
    _ser
    0.06
    éĤ£ä¹Łæĺ¯
    0.06
    Activations Density 0.015%

    No Known Activations