© 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. 37749
    Prev
    Next
    INDEX
    Explanations

    exponents and roots

    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
     sudd
    -0.08
    rott
    -0.08
    louv
    -0.08
     entier
    -0.08
    udeau
    -0.08
    åįĬ个
    -0.07
    ugas
    -0.07
    ChangeListener
    -0.07
    herits
    -0.07
    çĶŁæķĪä¹ĭæĹ¥èµ·
    -0.07
    POSITIVE LOGITS
    allis
    0.07
    arden
    0.07
    èij±èij±
    0.07
    å©·
    0.07
    Ļ
    0.06
    anken
    0.06
    anship
    0.06
    sem
    0.06
    apul
    0.06
    åĴĮæĦıä¹ī
    0.06
    Activations Density 0.002%

    No Known Activations