© 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. 15142
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

    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
    tat
    -0.09
    Syntax
    -0.08
    她èĩªå·±
    -0.07
    incon
    -0.07
    edith
    -0.07
    pat
    -0.07
    codegen
    -0.07
    æĪij个人
    -0.07
    yntax
    -0.07
    bourne
    -0.07
    POSITIVE LOGITS
    ember
    0.07
     liberty
    0.07
    çļĦ第ä¸Ģ天
    0.07
     Liberty
    0.07
     впеÑĢвÑĭе
    0.06
    润
    0.06
    æ±ĩ
    0.06
    æĹłåĩł
    0.06
     Lauf
    0.06
     Lib
    0.06
    Activations Density 0.027%

    No Known Activations