© 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. 19436
    Prev
    Next
    INDEX
    Explanations

    deep neural networks

    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
    åĩ«
    -0.08
    çĽIJåĴĮ
    -0.08
    uide
    -0.07
    geber
    -0.07
     swingers
    -0.07
    obar
    -0.07
    æݨå¼Ģ
    -0.07
    åĩºä¸Ģ份
    -0.07
    gespr
    -0.07
     Motel
    -0.07
    POSITIVE LOGITS
     models
    0.10
     trained
    0.09
     neural
    0.09
     architectures
    0.09
     model
    0.09
    ç»ĵæŀĦä¸İ
    0.09
     architecture
    0.09
    -powered
    0.09
     pretrained
    0.09
    model
    0.08
    Activations Density 0.053%

    No Known Activations