© 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. 4543
    Prev
    Next
    INDEX
    Explanations

    size of dimensions or quantities

    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
    à¥įस
    -0.10
    uzzi
    -0.10
     ÐľÐ¾ÑĢо
    -0.09
    avais
    -0.09
    aison
    -0.09
    shire
    -0.09
    à¸IJม
    -0.09
    zelf
    -0.09
     zdar
    -0.09
    minster
    -0.08
    POSITIVE LOGITS
    hood
    0.09
    ening
    0.09
    holder
    0.08
    Ùĭ
    0.07
    yka
    0.07
    leep
    0.07
    etting
    0.07
    gerald
    0.07
    ÅĻejmÄĽ
    0.07
    pread
    0.06
    Activations Density 0.046%

    No Known Activations