© 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. 48166
    Prev
    Next
    INDEX
    Explanations

    web, computer, and

    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
    à¸ģาร
    -0.15
    ä¸Ģ个
    -0.11
    ãĥ³
    -0.11
    à¸ģารสรà¹īาà¸ĩ
    -0.10
    اÙĨ
    -0.10
    à¸ģารà¸Īัà¸Ķà¸ģาร
    -0.10
    м
    -0.10
    对
    -0.10
    à¸ģารà¸Īัà¸Ķ
    -0.09
    an
    -0.09
    POSITIVE LOGITS
    Ø©
    0.13
    å¾Ģ常ä¸Ģæł·
    0.12
    /or
    0.09
    /of
    0.09
    иÑİ
    0.09
    ftime
    0.09
    thon
    0.09
    ignal
    0.09
    çħ¦
    0.09
    ниÑĨи
    0.09
    Activations Density 0.002%

    No Known Activations