© 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. 55145
    Prev
    Next
    INDEX
    Explanations

    example / exemple

    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
    è¿ĻäºĽä¸ľè¥¿
    -0.08
    è¿ĻäºĽäºĭæĥħ
    -0.07
    è¿ĻäºĽäºĭ
    -0.07
     major
    -0.07
    edium
    -0.07
    illac
    -0.07
    endas
    -0.06
    è¿ĻäºĽå°ı
    -0.06
    åįľ
    -0.06
    å°ıåħµ
    -0.06
    POSITIVE LOGITS
    çļĦä¾ĭåŃIJ
    0.10
    ä¾ĭåŃIJ
    0.09
     example
    0.09
    example
    0.09
     hypothetical
    0.09
    举个ä¾ĭåŃIJ
    0.09
    åħ¸åŀĭçļĦ
    0.09
     ìĺĪ를
    0.09
     illustrate
    0.09
    /example
    0.09
    Activations Density 0.035%

    No Known Activations