© 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. 12006
    Prev
    Next
    INDEX
    Explanations

    parallel lines and axes

    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
    ä¸į缺
    -0.08
    룬
    -0.07
    天ä¸ĭ
    -0.06
    å¾Ĵæīĭ
    -0.06
    åħįä¸įäºĨ
    -0.06
    eries
    -0.06
    èī¯
    -0.06
    æīĵ交éģĵ
    -0.06
    ä¸įåIJĮç¨ĭ度çļĦ
    -0.06
    çļĦèĭ¦
    -0.06
    POSITIVE LOGITS
    ç©¿è¿ĩ
    0.10
    ulp
    0.07
    _FN
    0.07
    plice
    0.07
    antz
    0.07
    isman
    0.07
    åĪļ好
    0.07
     parallel
    0.07
    parallel
    0.07
    à¸ģลาà¸ĩ
    0.07
    Activations Density 0.010%

    No Known Activations