© 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. 48187
    Prev
    Next
    INDEX
    Explanations

    combinations, subdivisions, stereoisomers, values, degrees of freedom

    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
    stech
    -0.08
    姥
    -0.08
    æĸ°ä¸Ģè½®
    -0.08
    isz
    -0.07
    leder
    -0.07
    alla
    -0.07
    个æĪĸå¤ļ个
    -0.07
    RAR
    -0.07
    obec
    -0.07
    }//
    -0.07
    POSITIVE LOGITS
    åı¯ä¾ĽéĢīæĭ©
    0.09
    ä¹ĭå¤ļ
    0.09
    åı¯ä¾Ľ
    0.08
     altogether
    0.08
    åı¯è¨Ģ
    0.08
    uve
    0.08
     altrett
    0.07
     ÙĪØ£Ùĥثر
    0.07
    æĹ¥åIJij
    0.07
    à¸Ķà¹īวยà¸ģัà¸Ļ
    0.06
    Activations Density 0.034%

    No Known Activations