© 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. 55284
    Prev
    Next
    INDEX
    Explanations

    younger brother

    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
    pes
    -0.08
    pth
    -0.08
    ehme
    -0.08
    ãĥ³ãĥĹ
    -0.08
    empt
    -0.08
     hardcore
    -0.08
     поÑĤÑĢа
    -0.08
    aum
    -0.08
    à´ļàµįà´ļ
    -0.08
    anner
    -0.08
    POSITIVE LOGITS
    igh
    0.09
    ãģ»ãģĨ
    0.08
    _than
    0.08
    æĹłæ¯ĶçļĦ
    0.07
    ä¸ĢäºĽçļĦ
    0.07
    rink
    0.07
     ones
    0.07
    ä¹Łæĺ¯æľĢ
    0.07
    -than
    0.07
    ترÛĮÙĨ
    0.07
    Activations Density 0.040%

    No Known Activations