© 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. 43631
    Prev
    Next
    INDEX
    Explanations

    oral potentially malignant disorders

    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
    ersh
    -0.09
     ÙĤص
    -0.08
    èį·åĮħ
    -0.07
    umd
    -0.07
    vence
    -0.07
    igli
    -0.07
    iski
    -0.07
    è¯ģæĺİ书
    -0.07
    ouro
    -0.07
    estream
    -0.07
    POSITIVE LOGITS
    èĭĶ
    0.13
    èħ»
    0.09
    è¦Ĩ
    0.09
    èĹ
    0.08
    -covered
    0.07
    éļıé£İ
    0.07
    æĪijçļĦç¥Ŀç¦ı
    0.07
    ë©´ìĹIJ
    0.07
    è¦ĨçĽĸ
    0.07
    ivery
    0.07
    Activations Density 0.001%

    No Known Activations