© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17718
    Prev
    Next
    INDEX
    Explanations

    numbers less than zero

    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
    åĪĩå®ŀæıIJé«ĺ
    -0.07
    orr
    -0.07
    either
    -0.07
    ä»İèĢĮå®ŀçİ°
    -0.07
     implements
    -0.07
    oday
    -0.07
    .bio
    -0.07
    ily
    -0.07
     either
    -0.07
    Whenever
    -0.07
    POSITIVE LOGITS
    åĺ¹
    0.07
    缮æłĩ
    0.07
    esen
    0.07
    eza
    0.07
    äºĨçĤ¹
    0.07
    eport
    0.06
     목íijľ
    0.06
    iedo
    0.06
    åĴĮ缮æłĩ
    0.06
    idot
    0.06
    Activations Density 0.001%

    No Known Activations