© 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. 11763
    Prev
    Next
    INDEX
    Explanations

    semantic differences

    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
    天å®ĩ
    -0.07
    eme
    -0.07
     combined
    -0.06
    éĢIJ项
    -0.06
    зиÑĢа
    -0.06
    ä¸įè¾ŀ
    -0.06
    åįķ项
    -0.06
     Combined
    -0.06
    combined
    -0.06
    ieger
    -0.06
    POSITIVE LOGITS
    æĸ°æŧ
    0.16
    对æ¯Ķ
    0.15
    åīįåIJİçļĦ
    0.14
    åīįåIJİ
    0.14
     difference
    0.13
    å·®
    0.12
    difference
    0.12
     ÑĢазниÑĨа
    0.12
     Difference
    0.12
    å·®é¢Ŀ
    0.12
    Activations Density 0.376%

    No Known Activations