© 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. 64765
    Prev
    Next
    INDEX
    Explanations

    code snippets and symbols

    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
    润
    -0.08
    è´°
    -0.07
    IOR
    -0.07
    менÑĥ
    -0.07
    éĩijåĪļ
    -0.07
    åĽĽå±Ĥ
    -0.07
    áĢģáĢ¼
    -0.07
    otur
    -0.07
    chtig
    -0.07
    å°ijåħĪ
    -0.07
    POSITIVE LOGITS
    ä¸İéĿŀ
    0.07
    ç»Ŀåľ°
    0.07
    æĪijçıŃ
    0.07
    erland
    0.07
    æľªåıĸå¾Ĺ
    0.07
     Unter
    0.07
    æĹ
    0.06
    æī«æıı仪
    0.06
    stab
    0.06
    _globals
    0.06
    Activations Density 0.073%

    No Known Activations