© 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. 9641
    Prev
    Next
    INDEX
    Explanations

    declarations with MAX, size, app

    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
    aghan
    -0.08
    缸åħ³æݨèįIJ
    -0.08
    çīĪæĿĥçŃī
    -0.08
    çģ«çº¿
    -0.07
    rica
    -0.07
    讲åłĤ
    -0.07
    iev
    -0.07
    reit
    -0.07
    åĿıäºĭ
    -0.07
    anness
    -0.07
    POSITIVE LOGITS
    éģĩåĪ°
    0.07
    çī©
    0.06
    DEV
    0.06
    ç¡
    0.06
    alp
    0.06
    etin
    0.06
    åŁº
    0.06
    WF
    0.06
    è½½
    0.06
    ujan
    0.06
    Activations Density 0.061%

    No Known Activations