© 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. 17849
    Prev
    Next
    INDEX
    Explanations

    progression

    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
    angelo
    -0.08
    istics
    -0.08
    à¹Ģà¸Īาะ
    -0.08
    à³įದ
    -0.08
    ugin
    -0.08
    à¸ģำà¹Ģà¸Ļิà¸Ķ
    -0.08
    geschoss
    -0.08
    à¸Ľà¸°
    -0.08
    igió
    -0.08
     Ñģебе
    -0.08
    POSITIVE LOGITS
    äºĨä¸ĢæŃ¥
    0.09
    ively
    0.08
    åĴĮå®ĮåĸĦ
    0.08
     pesat
    0.08
    -quarters
    0.07
    antly
    0.07
    ion
    0.07
     során
    0.07
    escu
    0.07
    åĿŀ
    0.07
    Activations Density 0.037%

    No Known Activations