© 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. 4854
    Prev
    Next
    INDEX
    Explanations

    powers of variables

    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
    äºİè¡Į
    -0.07
    umpt
    -0.06
    tox
    -0.06
    éĤ£åIJį
    -0.06
    iple
    -0.06
    æīĩéŨ
    -0.06
    tor
    -0.06
    UTE
    -0.06
    举éŨ
    -0.06
    çļĦéĤ£ä¸ªäºº
    -0.06
    POSITIVE LOGITS
     squared
    0.09
     квадÑĢ
    0.09
     quadratic
    0.09
    ByVersion
    0.08
    abora
    0.08
    _squared
    0.08
    emmin
    0.08
    å¹³æĸ¹
    0.08
     квадÑĢаÑĤ
    0.07
     quart
    0.07
    Activations Density 0.011%

    No Known Activations