© 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. 48293
    Prev
    Next
    INDEX
    Explanations

    scientific method and results

    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
    æ²»çIJĨèĥ½åĬĽ
    -0.08
    æĺİå¹´
    -0.08
    stakes
    -0.07
    å¾Īè¾Ľèĭ¦
    -0.07
    åIJĮå¿Ĺ为
    -0.07
    иж
    -0.07
    .languages
    -0.07
    åįİé¾Ļ
    -0.07
    壮大çļĦ
    -0.07
    óf
    -0.07
    POSITIVE LOGITS
    御
    0.09
    对æīĢ
    0.07
    arit
    0.07
    ä¼¼çļĦ
    0.07
    o
    0.06
    èĵ¬
    0.06
    angkan
    0.06
    迸
    0.06
    梦
    0.06
    åħĢ
    0.06
    Activations Density 1.133%

    No Known Activations