© 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. 4860
    Prev
    Next
    INDEX
    Explanations

    method calls

    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
    _SUITE
    -0.06
    ä¸įèĩª
    -0.06
    æį²
    -0.06
     contrac
    -0.06
    æĺ¯ä¸įåIJĮçļĦ
    -0.06
    araf
    -0.06
    梦
    -0.06
    ?s
    -0.06
     Prior
    -0.06
    æīĢåѦçļĦ
    -0.06
    POSITIVE LOGITS
    æĺĤ
    0.08
     */)
    0.07
    ieszcz
    0.07
    avion
    0.07
    çĶŁæķĪä¹ĭæĹ¥èµ·
    0.07
    rzy
    0.07
    aving
    0.07
    ÑĢока
    0.07
    ierungs
    0.07
    åIJ«éĩij
    0.07
    Activations Density 0.069%

    No Known Activations