© 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. 50527
    Prev
    Next
    INDEX
    Explanations

    `id` followed by colon

    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
    anton
    -0.08
    ingi
    -0.07
    empor
    -0.07
    ing
    -0.07
    æīĢæĮģ
    -0.06
    æĮģ
    -0.06
    åĴ«å°º
    -0.06
    agli
    -0.06
    andr
    -0.06
    erot
    -0.06
    POSITIVE LOGITS
    ologo
    0.08
    åı¯è¨Ģ
    0.08
    ATYPE
    0.07
    !!!!!!!!
    0.07
    ELY
    0.07
    rollo
    0.07
    yel
    0.07
    verz
    0.07
    -sale
    0.07
    åIJĮè¡Įä¸ļ
    0.07
    Activations Density 0.001%

    No Known Activations