© 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. 44067
    Prev
    Next
    INDEX
    Explanations

    smallest value

    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
    å°Ķ
    -0.07
     fol
    -0.07
    %B
    -0.06
    çĥ
    -0.06
    ovn
    -0.06
     bezieh
    -0.06
    以ä¸Ģç§į
    -0.06
     unavoid
    -0.06
    æĥľ
    -0.06
    åİ»åIJij
    -0.06
    POSITIVE LOGITS
    нÑĮ
    0.08
    again
    0.08
    åIJĮä¸Ĭ
    0.08
    åıĪæĺ¯ä¸Ģ个
    0.07
    ulia
    0.07
    erts
    0.07
    ular
    0.07
    ಡಿ
    0.07
    åĨįãģ³
    0.07
    åľ¨æŀĹ
    0.07
    Activations Density 0.038%

    No Known Activations