© 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. 56716
    Prev
    Next
    INDEX
    Explanations

    growth factor beta

    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
    é¦Ļæ²¹
    -0.07
    åĢ¼çıŃ
    -0.06
     ARR
    -0.06
    丹éľŀ
    -0.06
     Arr
    -0.06
    念念ä¸įå¿ĺ
    -0.06
    çķĻé¦Ļ
    -0.06
    arr
    -0.06
    温差
    -0.06
    lap
    -0.06
    POSITIVE LOGITS
     Kushner
    0.08
    apult
    0.08
     autod
    0.08
    åĽ³æĽ¸
    0.08
    lanz
    0.08
    à¹Īำ
    0.07
    denes
    0.07
    æ´»ä¸ĭåİ»
    0.07
    ussia
    0.07
    lon
    0.07
    Activations Density 0.148%

    No Known Activations