© 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. 65071
    Prev
    Next
    INDEX
    Explanations

    code block closing 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
    è¿Ļä¸Ģå¹´
    -0.07
     determin
    -0.06
    con
    -0.06
    çļĦä¸ĢèĪ¬
    -0.06
    @@
    -0.06
    aw
    -0.06
     оп
    -0.06
    æ²³çļĦ
    -0.06
    åºĶ该
    -0.06
    river
    -0.06
    POSITIVE LOGITS
    elh
    0.10
    uche
    0.09
    WithPath
    0.08
    Äĥt
    0.08
    uai
    0.08
    ayet
    0.08
    WithData
    0.08
    æĪIJç«ĭ
    0.08
    ubr
    0.08
    ä¸įæĻĤ
    0.08
    Activations Density 0.181%

    No Known Activations