© 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. 34292
    Prev
    Next
    INDEX
    Explanations

    code comments and metadata

    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
    .mit
    -0.08
    说äºĨ
    -0.07
    által
    -0.07
     Rücks
    -0.07
    ival
    -0.06
    è¯ĿéŁ³
    -0.06
     innov
    -0.06
    £
    -0.06
    ÙĦØ·
    -0.06
     Viagra
    -0.06
    POSITIVE LOGITS
    æĦŁæĥ³
    0.07
    ç´IJ
    0.07
     ("<
    0.07
    æ©
    0.07
    atori
    0.06
    ä¸Ģ路走æĿ¥
    0.06
    omás
    0.06
    keur
    0.06
    ủng
    0.06
    kor
    0.06
    Activations Density 0.048%

    No Known Activations