© 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. 45214
    Prev
    Next
    INDEX
    Explanations

    programmatic concepts

    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¸ŃéĹ´
    -0.07
    è¿Ľåħ¥
    -0.07
     oci
    -0.06
    鬼
    -0.06
    ä¸Ńå¤ĸ
    -0.06
    é¦ĸåħĪ
    -0.06
    .com
    -0.06
    åĬłçĽŁ
    -0.06
    else
    -0.06
    çħ§
    -0.06
    POSITIVE LOGITS
     ÂŃ
    0.09
     âĢİ
    0.08
    水产åĵģ
    0.08
    ÙĭÙijا
    0.07
     (âĢ¦)
    0.07
    /topic
    0.07
    woke
    0.07
     нежи
    0.07
    带åİ»
    0.07
    Advertisement
    0.07
    Activations Density 0.005%

    No Known Activations