© 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. 32053
    Prev
    Next
    INDEX
    Explanations

    not an expert, unfamiliar with specific technical terms

    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
    agas
    -0.08
    pite
    -0.07
    ÙĩÙī
    -0.07
    chette
    -0.07
    åĴĮåIJĪä½ľ
    -0.07
     Äijiá»ĩp
    -0.07
    ãģ¾ãģĽãĤĵãģĭ
    -0.07
     ìłķìĿĺ
    -0.07
    aison
    -0.07
    andin
    -0.07
    POSITIVE LOGITS
    ä¸ĵä¸ļçŁ¥è¯Ĩ
    0.13
    æĸ¹éĿ¢çļĦçŁ¥è¯Ĩ
    0.12
     expertise
    0.11
     terminology
    0.10
     expert
    0.10
     specifics
    0.10
     intric
    0.10
    ä¸įæĩĤ
    0.10
    ä¸įçĨŁæĤī
    0.10
     unfamiliar
    0.10
    Activations Density 0.607%

    No Known Activations