© 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. 33208
    Prev
    Next
    INDEX
    Explanations

    file paths and code snippets

    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
    _mapper
    -0.07
    eor
    -0.07
    ×ŀ×Ļ×Ŀ
    -0.07
    luck
    -0.07
    åĢĴ
    -0.07
    ukum
    -0.06
    à¤Ľ
    -0.06
    ä¹Łè·ŁçĿĢ
    -0.06
    åıĺæĪIJä¸Ģ个
    -0.06
    ãĢĤï¼Ī
    -0.06
    POSITIVE LOGITS
    etre
    0.08
    åħ¨éĥ¨è¯Ħ论
    0.07
    duc
    0.07
     ÙĨÙģسÙĩ
    0.07
     ÙħÙĨت
    0.07
    reas
    0.07
     irresist
    0.07
     ÄijÃŃch
    0.07
    .NewRequest
    0.06
    brane
    0.06
    Activations Density 0.043%

    No Known Activations