© 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. 47662
    Prev
    Next
    INDEX
    Explanations

    simple, beginner, or grade level

    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»ĺ
    -0.08
    è¦ģåħĪ
    -0.07
    å¯IJ
    -0.07
    å¿ħé¡»åħĪ
    -0.07
    казаниÑı
    -0.07
     nude
    -0.07
    裸
    -0.07
    åīĥ
    -0.07
    à¸Ĺุà¸ģà¸Ĥà¹Į
    -0.06
    ogne
    -0.06
    POSITIVE LOGITS
    ç®ĢåįķçļĦ
    0.11
    ç®Ģæĺĵ
    0.11
     simplicity
    0.11
     simpler
    0.10
     Simple
    0.10
    ç®Ģåįķ
    0.10
    /simple
    0.10
    simple
    0.10
     simple
    0.09
    -simple
    0.09
    Activations Density 0.115%

    No Known Activations