© 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. 16236
    Prev
    Next
    INDEX
    Explanations

    approximation and equality signs

    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
    igon
    -0.09
    wass
    -0.08
    wich
    -0.08
    wig
    -0.08
    коно
    -0.08
    halle
    -0.08
    inous
    -0.08
    icch
    -0.07
    设计ä¸Ĭ
    -0.07
    ç¼łç»µ
    -0.07
    POSITIVE LOGITS
    渡ãģĹ
    0.07
    ä»Ģä¹Īåij¢
    0.06
    åĪĨ
    0.06
    æķĪ
    0.06
    äºİæĺ¯
    0.06
    ç¨ĭ度
    0.06
    ably
    0.06
    æݧèĤ¡éĽĨåĽ¢
    0.06
    被
    0.06
     Peyton
    0.06
    Activations Density 0.001%

    No Known Activations