© 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. 41028
    Prev
    Next
    INDEX
    Explanations

    now followed by context

    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
     otherwise
    -0.09
    eram
    -0.09
    /proto
    -0.09
    er
    -0.08
    aster
    -0.08
    ãĤĪãģĨãģ«ãģªãģ£ãģ¦
    -0.08
    æľĢç»Īè¿ĺæĺ¯
    -0.08
    åIJ¦åĪĻä¼ļ
    -0.08
     ultimately
    -0.08
    otherwise
    -0.08
    POSITIVE LOGITS
    adays
    0.11
    że
    0.10
    mehr
    0.09
    éĹ®é¢ĺæĿ¥äºĨ
    0.09
    çļĦéĹ®é¢ĺæĺ¯
    0.08
    ness
    0.08
    èĨĽ
    0.07
    ä¸į失
    0.07
    ÑĪ
    0.07
    iations
    0.07
    Activations Density 0.013%

    No Known Activations