© 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. 61663
    Prev
    Next
    INDEX
    Explanations

    movement or direction

    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
    åĩºæĿ¥åIJİ
    -0.09
    åĩºä¸Ģ
    -0.09
    åĩºåı£
    -0.09
    åĩºèĩªå·±çļĦ
    -0.09
    åĩºæĿ¥äºĨ
    -0.09
    æ»ijèIJ½
    -0.08
    åĩº
    -0.08
     export
    -0.08
    åĩºåı£çļĦ
    -0.08
    èĩªä¿¡åĴĮ
    -0.08
    POSITIVE LOGITS
     inputs
    0.11
    inputs
    0.11
     input
    0.10
     INPUT
    0.10
    è¾ĵåħ¥
    0.10
     Input
    0.10
    INPUT
    0.10
    Input
    0.10
     Inputs
    0.10
    input
    0.10
    Activations Density 0.003%

    No Known Activations