© 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. 4702
    Prev
    Next
    INDEX
    Explanations

    limit of, limit on, limit distributions

    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
    临åħ¶
    -0.09
    ness
    -0.09
    ifice
    -0.09
    ometrics
    -0.08
    ริà¸ĩ
    -0.08
    éĻIJäºİ
    -0.08
    entication
    -0.08
    åĽŀäºĭ
    -0.07
    峪
    -0.07
    sembly
    -0.07
    POSITIVE LOGITS
    ting
    0.08
    ì§Ģìĸ´
    0.08
    ungan
    0.07
    åĢ¼
    0.07
    ĺ
    0.07
     наÑģÑĤÑĥп
    0.07
    lessly
    0.07
    less
    0.07
    te
    0.07
    ateral
    0.07
    Activations Density 0.013%

    No Known Activations