© 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. 39359
    Prev
    Next
    INDEX
    Explanations

    sharing thoughts or process

    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
    agnol
    -0.08
    amon
    -0.08
    anker
    -0.08
    çľ¼è§Ĵ
    -0.07
     duplicated
    -0.07
    _EMIT
    -0.07
     Wonderland
    -0.07
    retti
    -0.07
    пеÑĨ
    -0.07
    ouce
    -0.07
    POSITIVE LOGITS
    Į¨
    0.07
    è·¯éĢı
    0.07
     selection
    0.07
    thinking
    0.07
    Sn
    0.07
    åĸ
    0.06
    ought
    0.06
    راض
    0.06
     thinking
    0.06
    _while
    0.06
    Activations Density 0.001%

    No Known Activations