© 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. 55238
    Prev
    Next
    INDEX
    Explanations

    cyclic formation

    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
    est
    -0.07
    à¸Ĺà¹Į
    -0.07
    olocation
    -0.07
    egn
    -0.07
    ieto
    -0.07
    鸿
    -0.07
    âĵĴ
    -0.07
    ep
    -0.07
    æ°´å¹³çļĦ
    -0.07
    glas
    -0.06
    POSITIVE LOGITS
     formation
    0.10
     Formation
    0.09
     formed
    0.09
    Formation
    0.09
     formations
    0.09
    aisen
    0.08
    çļĦå½¢æĪIJ
    0.08
     forming
    0.08
    ULAR
    0.08
    aight
    0.08
    Activations Density 0.011%

    No Known Activations