© 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. 21564
    Prev
    Next
    INDEX
    Explanations

    lines, segments, and spaces

    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
    asar
    -0.08
    åĪĨ项
    -0.08
    åĪĨéĥ¨
    -0.08
    羽翼
    -0.07
    å·´å¡ŀ
    -0.07
    çĪ¬åĿ¡
    -0.07
    thouse
    -0.07
    æ¡¥åĮº
    -0.07
    ilar
    -0.07
    incer
    -0.07
    POSITIVE LOGITS
     иÑģк
    0.08
     intersect
    0.08
     uniquely
    0.08
    延伸
    0.07
    绵
    0.07
     unique
    0.07
    intersect
    0.07
     unic
    0.07
    åIJ»
    0.07
     intersects
    0.06
    Activations Density 0.006%

    No Known Activations