© 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. 32742
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and code constructs

    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
     while
    -0.07
     vs
    -0.07
    ×Ŀ
    -0.06
     key
    -0.06
     **
    -0.06
    è¶Ĭéķ¿
    -0.06
    -0.06
    ä¸īäºĶ
    -0.05
    ade
    -0.05
    *
    -0.05
    POSITIVE LOGITS
    SYM
    0.10
    æĪĸå°ij
    0.09
    oghi
    0.08
    æīĢåľ¨ä½įç½®
    0.08
    è¦ģä¸įçĦ¶
    0.08
    ÉĻlÉĻ
    0.08
    æ£ł
    0.08
    ùy
    0.08
    uxt
    0.08
    ÑĢиÑģÑĤа
    0.08
    Activations Density 0.023%

    No Known Activations