© 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. 47566
    Prev
    Next
    INDEX
    Explanations

    aptitude question

    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¦ģ
    -0.08
    褥
    -0.08
    γÏģα
    -0.08
    åįİåºŃ
    -0.07
    éľ²
    -0.07
     insisti
    -0.07
    é«ĺä¸Ģ
    -0.07
     Uncategorized
    -0.07
    HDR
    -0.07
    áŀİ
    -0.07
    POSITIVE LOGITS
    åĽ½èĢĥ
    0.08
    yak
    0.07
    yna
    0.07
    æĸĹ
    0.07
    è¡Įæµĭ
    0.07
    ä¸Ńåħ¬
    0.06
     nest
    0.06
    æĭĽèĢĥ
    0.06
    reek
    0.06
    roit
    0.06
    Activations Density 0.002%

    No Known Activations