© 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. 26780
    Prev
    Next
    INDEX
    Explanations

    functions complementary

    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
    ä¾ĽåºĶ产åĵģ
    -0.08
    à¹ģà¸Ķà¸Ļ
    -0.08
    å¿ħ究
    -0.07
     consenting
    -0.07
    ÑģмоÑĤÑĢиÑĤе
    -0.07
    åĪĢçīĩ
    -0.07
     Bint
    -0.07
    ersch
    -0.07
    ubl
    -0.07
    以赴
    -0.07
    POSITIVE LOGITS
    èĭ¦
    0.07
     accum
    0.07
    éĨ
    0.07
    æľŁåĨħ
    0.07
    è¯ķè¡Į
    0.06
     Multip
    0.06
    æĶĺ
    0.06
     Rosenstein
    0.06
     integrating
    0.06
    pac
    0.06
    Activations Density 0.001%

    No Known Activations