© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 45257
    Prev
    Next
    INDEX
    Explanations

    how to convert or render

    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
     splitted
    -0.12
     nowadays
    -0.12
     Nowadays
    -0.10
     utmost
    -0.10
    Moreover
    -0.10
     functionalities
    -0.10
     Moreover
    -0.09
     equipments
    -0.08
     moreover
    -0.08
     till
    -0.08
    POSITIVE LOGITS
    unen
    0.08
     ostensibly
    0.07
    åĽ½éŨ
    0.07
    æīİåħĭ
    0.07
    éĺ³åİ¿
    0.07
     disparate
    0.07
    communications
    0.07
    ature
    0.07
     cleanly
    0.07
    æĮīæľĪ
    0.07
    Activations Density 3.875%

    No Known Activations