© 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. 4628
    Prev
    Next
    INDEX
    Explanations

    latex math subscripts

    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
    orno
    -0.07
    gau
    -0.07
    ament
    -0.07
    åij»
    -0.07
    å®Įç¾İçļĦ
    -0.07
    _OLD
    -0.07
     shootout
    -0.07
    Commit
    -0.07
    _AUTO
    -0.06
    åħ¼
    -0.06
    POSITIVE LOGITS
    ichte
    0.07
    æľĪæ´»åĬ¨
    0.07
    μά
    0.07
    Ñīем
    0.07
     others
    0.07
    ä¸ĢæĿij
    0.07
    itches
    0.07
    åľ°å¤´
    0.07
    mate
    0.07
     acquis
    0.07
    Activations Density 0.001%

    No Known Activations