© 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. 10738
    Prev
    Next
    INDEX
    Explanations

    mathematical comparisons and calculations

    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
    ä¸įéĢĢ
    -0.07
    ĴĪ
    -0.07
    驻马
    -0.07
    mue
    -0.07
    iples
    -0.07
     herum
    -0.07
    ully
    -0.06
    ipple
    -0.06
    ĮĢ
    -0.06
    eward
    -0.06
    POSITIVE LOGITS
    æĺĩ
    0.07
    çĻ½å±±
    0.07
    ä¸ŃçļĦä¸Ģ
    0.06
    odon
    0.06
    åįģéĩĮ
    0.06
     barat
    0.06
    antro
    0.06
    osci
    0.06
     sett
    0.06
    ailles
    0.06
    Activations Density 0.010%

    No Known Activations