© 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. 26096
    Prev
    Next
    INDEX
    Explanations

    models and development

    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
     Certific
    -0.08
    utage
    -0.07
    casecmp
    -0.07
    éĢļ常ãģ®
    -0.07
    ÅĤuga
    -0.07
     spoiled
    -0.07
    mane
    -0.07
    engar
    -0.07
    å¸Ĥåľºä¸ĬçļĦ
    -0.07
    åıĮåıĮ
    -0.07
    POSITIVE LOGITS
     models
    0.15
    模åŀĭ
    0.14
     model
    0.13
    建模
    0.13
    模åŀĭçļĦ
    0.13
    model
    0.12
     modeling
    0.11
    /model
    0.11
     modelling
    0.11
    /models
    0.11
    Activations Density 0.124%

    No Known Activations