© 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. 16494
    Prev
    Next
    INDEX
    Explanations

    chemical conversions and reactions

    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
    ä¸įä¸ĭ
    -0.06
    edes
    -0.06
    çľĭ
    -0.06
     overhead
    -0.06
    ostat
    -0.06
    igni
    -0.05
    ãģŁãģ¨
    -0.05
    å¦ĤæŀľæĬĬ
    -0.05
    .pb
    -0.05
    å¹³æŶ
    -0.05
    POSITIVE LOGITS
     afterwards
    0.09
    aney
    0.09
    å¾ĹåĪ°ä¸Ģ个
    0.09
    è¿ĻæĿ¡è·¯
    0.08
    è¿Ļä¸ĢæŃ¥
    0.08
    ertura
    0.08
    åIJİçĶ¨
    0.08
    ãģ©ãĤĬ
    0.08
    Via
    0.08
     Desired
    0.08
    Activations Density 0.044%

    No Known Activations