© 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. 39833
    Prev
    Next
    INDEX
    Explanations

    of each individual

    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
    æ²¥
    -0.07
    ä»ĸåij½
    -0.07
    rix
    -0.06
    à¸Ļà¸Ńà¸ĩ
    -0.06
    acious
    -0.06
    åĢį
    -0.06
    è¯Ŀ
    -0.06
    hafen
    -0.06
    ioc
    -0.06
    对æĸ¹çļĦ
    -0.06
    POSITIVE LOGITS
     einzelnen
    0.09
     jednotliv
    0.09
     individual
    0.08
     ÙĪعدد
    0.08
     newly
    0.08
     each
    0.08
    åįķ个
    0.08
     enkelt
    0.07
     từng
    0.07
     pojed
    0.07
    Activations Density 0.152%

    No Known Activations