© 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. 19319
    Prev
    Next
    INDEX
    Explanations

    sit or seating and chairs

    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
    ryn
    -0.08
    èıľåĪĢ
    -0.08
     marching
    -0.08
     march
    -0.07
    SSI
    -0.06
    å¥Ķèµ°
    -0.06
    èĪŀæĽ²
    -0.06
    è·¯ä¸Ĭ
    -0.06
    ertz
    -0.06
    åĭ¤æģ³
    -0.06
    POSITIVE LOGITS
    座æ¤ħ
    0.13
     seating
    0.12
     seats
    0.12
    å¸Ń
    0.12
     seat
    0.12
    åĿIJä¸ĭ
    0.12
     wygod
    0.11
     chairs
    0.11
    åĿIJä¸ĭæĿ¥
    0.11
     ngá»ĵi
    0.11
    Activations Density 0.103%

    No Known Activations