© 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. 13996
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation

    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
    craft
    -0.10
    ами
    -0.10
    erior
    -0.09
    ¾
    -0.08
    undra
    -0.08
    ppure
    -0.08
    æĸĩåĵ²
    -0.08
     Publicada
    -0.08
    并讲è¯Ŀ
    -0.08
    manship
    -0.08
    POSITIVE LOGITS
    ÙĴ
    0.08
    аÑĤÑĮ
    0.08
    ired
    0.07
    æĪij们æīĢ
    0.07
    ed
    0.07
    ло
    0.07
     razu
    0.07
    ì§ĵ
    0.06
     quite
    0.06
    ar
    0.06
    Activations Density 0.001%

    No Known Activations