© 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. 18618
    Prev
    Next
    INDEX
    Explanations

    hours a day

    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
    æĪĸåħ¶
    -0.07
    åıĬåħ¶ä»ĸ
    -0.07
    ä¾µ
    -0.07
    ondes
    -0.07
    åıĬåħ¶
    -0.07
    ental
    -0.07
    ä¸Ģèĩ³
    -0.07
    ס×Ķ
    -0.06
    æĪĸåħ¶ä»ĸ
    -0.06
    UTH
    -0.06
    POSITIVE LOGITS
    ãĢģ
    0.12
     ãĢģ
    0.09
    ､
    0.08
    丶
    0.08
    åħ®
    0.07
    ideo
    0.07
    ãĢģãĢİ
    0.07
    tter
    0.07
    รม
    0.06
    ,column
    0.06
    Activations Density 0.293%

    No Known Activations