© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34160
    Prev
    Next
    INDEX
    Explanations

    even though or despite

    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
    èIJ½èIJ½
    -0.07
    .checked
    -0.07
     anything
    -0.07
    åıĹä¸įäºĨ
    -0.07
    æģ°å¥½
    -0.07
    ä¹ĭ交
    -0.07
    izable
    -0.06
    太强
    -0.06
    ones
    -0.06
    à¸Īะà¹Ħà¸Ľ
    -0.06
    POSITIVE LOGITS
    çľĭä¼¼
    0.11
     seemingly
    0.09
    çľĭä¸Ĭåİ»
    0.08
     Despite
    0.08
    身å¤Ħ
    0.08
    chein
    0.08
    è²Įä¼¼
    0.08
    Despite
    0.08
     seeming
    0.08
     officially
    0.08
    Activations Density 0.213%

    No Known Activations