© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 825
    Prev
    Next
    INDEX
    Explanations

    Albert Einstein

    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
    ség
    -0.09
    uesta
    -0.08
    两åѦä¸Ģåģļ
    -0.08
    ãĢħ
    -0.08
    ä¸ĭå¿ĥ
    -0.08
    å¾ĢæľŁç²¾å½©
    -0.08
    sst
    -0.08
    ×Ļס
    -0.08
    itamin
    -0.08
    ////////////////////////////////////////////////////////////////////////////
    -0.07
    POSITIVE LOGITS
    HING
    0.07
    ä¸īçĶŁ
    0.06
    å¨ľ
    0.06
    é¢ĺæĦı
    0.06
    ories
    0.06
    orÃŃas
    0.06
    å¹³æ¹ĸ
    0.06
    °
    0.06
    åĢijçļĦ
    0.06
    ification
    0.06
    Activations Density 0.005%

    No Known Activations