© 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. 34849
    Prev
    Next
    INDEX
    Explanations

    biological, scientific, or medical conditions and phenomena

    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
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    -0.07
    ä¹ĭçľ¼
    -0.07
    vard
    -0.07
    udder
    -0.06
    алÑĮ
    -0.06
    /=
    -0.06
    çļĦåģļæ³ķ
    -0.06
    inal
    -0.06
    ppv
    -0.06
     vard
    -0.06
    POSITIVE LOGITS
    次éĺħ读
    0.07
    enz
    0.07
    ä¸Ģéĥİ
    0.07
    lessly
    0.07
    anton
    0.06
    sr
    0.06
    ipsoid
    0.06
    ä¸Ĭæ·»
    0.06
    _sg
    0.06
    sg
    0.06
    Activations Density 0.357%

    No Known Activations