© 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. 8301
    Prev
    Next
    INDEX
    Explanations

    measurement of quantities

    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
    onge
    -0.08
    zung
    -0.07
    æĢ§å¼º
    -0.07
     cuy
    -0.07
    çī¹æľī
    -0.07
    jal
    -0.07
    æłĩè¯Ĩçłģ
    -0.07
    åIJįçĤº
    -0.07
    åIJį为
    -0.06
    天çĽĸ
    -0.06
    POSITIVE LOGITS
     measurement
    0.09
     measured
    0.08
    计çļĦ
    0.08
    æµĭå®ļ仪
    0.08
    å½±åĵįåĽłç´ł
    0.08
     estimation
    0.08
    ENTITY
    0.08
    æµĭéĩı
    0.08
     measurements
    0.08
    æĺ¯å¤ļå°ij
    0.08
    Activations Density 0.228%

    No Known Activations