© 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. 24014
    Prev
    Next
    INDEX
    Explanations

    listing separators/continuation

    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
    Containing
    -0.07
     Firstly
    -0.07
    çļĦä¸Ģ端
    -0.07
    yi
    -0.06
    åĦ¿æŶ
    -0.06
    à¹Ģà¸Ķิม
    -0.06
    amani
    -0.06
    amac
    -0.06
    æĹ¥æĬ¥
    -0.06
    alion
    -0.06
    POSITIVE LOGITS
    åı¯è§ģ
    0.08
    ä¸Ģ缴åĪ°
    0.08
     seterusnya
    0.08
    åı¯è¦ĭ
    0.08
    åı¯ä»¥çľĭåĩº
    0.08
    缴èĩ³
    0.07
     usw
    0.07
    çŃīçŃī
    0.07
    à¥įरा
    0.07
     etc
    0.07
    Activations Density 0.017%

    No Known Activations