© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61811
    Prev
    Next
    INDEX
    Explanations

    numbers, statistics, or specific entities

    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
    queira
    -0.07
    åºĶæīĭ
    -0.07
    emas
    -0.07
    è¢ħè¢ħ
    -0.07
    éĢļåĪĻ
    -0.07
    ÙĪÙĩ
    -0.07
    empf
    -0.07
    åĬªåĬĽåģļåĪ°
    -0.07
    eline
    -0.07
    ãģ¥
    -0.07
    POSITIVE LOGITS
    è¡ĮåĪĹ
    0.08
    avis
    0.08
    loyd
    0.07
    erator
    0.07
    aru
    0.07
    werk
    0.07
    à¸Ļัà¸Ķ
    0.07
     actions
    0.07
    ฯ
    0.07
    heck
    0.07
    Activations Density 0.006%

    No Known Activations