© 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. 9761
    Prev
    Next
    INDEX
    Explanations

    IU/kg or ml

    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
    axter
    -0.08
    bate
    -0.07
    cal
    -0.07
    اة
    -0.07
    جات
    -0.07
    å¹»
    -0.07
    ossi
    -0.07
    Tan
    -0.07
    veu
    -0.07
    æİĢèµ·
    -0.07
    POSITIVE LOGITS
    ÑĢиÑĤ
    0.07
    iley
    0.07
    adays
    0.07
    åĴĮä¹īåĬ¡
    0.07
    å¿ĥåĬ¨
    0.07
    ness
    0.06
    rit
    0.06
    å²±
    0.06
    inski
    0.06
    çĴĭ
    0.06
    Activations Density 0.001%

    No Known Activations