© 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. 717
    Prev
    Next
    INDEX
    Explanations

    STRM, Harry, Cir, positive

    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
    Negative Logits
    neys
    -0.07
     {}.
    -0.06
    ç«ĭåį³ä¸ĭè½½
    -0.06
    åĽ¢æĪIJåijĺ
    -0.06
     {};
    -0.06
    åĴ¬çĿĢ
    -0.06
    ULA
    -0.06
    _contin
    -0.06
     Gara
    -0.06
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.06
    POSITIVE LOGITS
    адÑĮ
    0.08
    aix
    0.07
    ugend
    0.07
     cocok
    0.07
    tright
    0.07
    کت
    0.07
    ARGET
    0.07
     STDERR
    0.07
    IRM
    0.07
    _FILENAME
    0.07
    Activations Density 0.026%

    No Known Activations