© 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. 44783
    Prev
    Next
    INDEX
    Explanations

    itself or edges

    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
    æĸĻ
    -0.07
    éļ¾å¾Ĺ
    -0.07
     breakdown
    -0.07
     decline
    -0.07
    Unload
    -0.06
     declined
    -0.06
    _estimator
    -0.06
     stocked
    -0.06
    EST
    -0.06
    涵åħ»
    -0.06
    POSITIVE LOGITS
    rips
    0.09
    rowse
    0.07
     equivalence
    0.07
    ç¼ĿåIJĪ
    0.07
    UTH
    0.07
    æĮĩå®ļçļĦ
    0.07
    utures
    0.07
    è£ĺ
    0.07
    éré
    0.07
    isons
    0.07
    Activations Density 0.008%

    No Known Activations