© 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. 55713
    Prev
    Next
    INDEX
    Explanations

    dashboard or ui text labels

    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
    Interested
    -0.06
    CI
    -0.06
     quasi
    -0.06
    åįģäºĮç«ł
    -0.06
    elling
    -0.06
    enga
    -0.06
     pageNo
    -0.06
    åıijæī¬
    -0.05
    æĿ¥ä¹ĭ
    -0.05
     `'
    -0.05
    POSITIVE LOGITS
    boll
    0.09
    æĶ¾ä¸įä¸ĭ
    0.08
    æĹ¶è¡¨ç¤º
    0.08
    yez
    0.08
    [number
    0.08
    سÙĪب
    0.07
    èİŀ
    0.07
    [__
    0.07
    overy
    0.07
    arnya
    0.07
    Activations Density 0.059%

    No Known Activations