© 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. 41838
    Prev
    Next
    INDEX
    Explanations

    mathematical 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
    opin
    -0.07
    uffs
    -0.07
    å¹´åĪĿ
    -0.07
    æĸ¹ãģ§
    -0.07
    jang
    -0.06
    cev
    -0.06
    ój
    -0.06
    heimer
    -0.06
    طر
    -0.06
    Wür
    -0.06
    POSITIVE LOGITS
    ograf
    0.07
    å²Ĺ
    0.07
    DOMNode
    0.07
    گاÙĩ
    0.07
    åĬ¿
    0.07
    åľ°ä½įçļĦ
    0.07
    æ³Ĭå°Ķ
    0.07
    åıĪæĿ¥
    0.07
    ä½ķ以
    0.07
    å´Ĺ
    0.07
    Activations Density 0.003%

    No Known Activations