© 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. 23251
    Prev
    Next
    INDEX
    Explanations

    medical and technical terms

    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
     же
    -0.09
    ologically
    -0.09
    æĢ§åľ°
    -0.08
    arser
    -0.08
    ively
    -0.07
    oriously
    -0.07
    ä¸ĬåĴĮ
    -0.07
    oret
    -0.07
    urally
    -0.07
    arer
    -0.07
    POSITIVE LOGITS
    Æ°Æ¡n
    0.08
    èĴĻå¾·
    0.08
    ãĥ¤ãĥ¼
    0.08
    ként
    0.07
    è¡ĢçĹĩ
    0.07
    ainties
    0.07
    åĴĮèī¯å¥½çļĦ
    0.07
    imony
    0.07
    ÑĨо
    0.07
    iah
    0.07
    Activations Density 1.587%

    No Known Activations