© 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. 30095
    Prev
    Next
    INDEX
    Explanations

    mathematical operators and variables

    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
    æ¦ķ
    -0.07
    INC
    -0.07
    èģĶ
    -0.07
    pid
    -0.07
    Ïģε
    -0.07
    ungan
    -0.07
    æĩ¿
    -0.07
    Latch
    -0.07
    åħ¬å®³
    -0.06
    鼷æĸ¯
    -0.06
    POSITIVE LOGITS
    otland
    0.07
    èĽĭ
    0.06
    ÙĤر
    0.06
    íĺ¼
    0.06
    æĤ²æ¬¢
    0.06
    rosse
    0.06
    é¦Ļ
    0.06
    ciano
    0.06
    isar
    0.06
    é¸Ń
    0.06
    Activations Density 0.039%

    No Known Activations