© 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. 49158
    Prev
    Next
    INDEX
    Explanations

    integral notation with indices

    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¦Ĥæŀľä¸įèĥ½
    -0.08
    模æĭŁé¢ĺ
    -0.07
    é»ĺ认çļĦ
    -0.07
    å®ļæľŁè¿Ľè¡Į
    -0.06
    æľĢ令人
    -0.06
    amus
    -0.06
    é»ĺ
    -0.06
     Schumer
    -0.06
    orman
    -0.06
     reserved
    -0.06
    POSITIVE LOGITS
    éĩijåŁİ
    0.08
    èĢ¦åIJĪ
    0.08
    宵
    0.08
    éĤ
    0.07
    个æľĪåīį
    0.07
    碰
    0.07
     mixing
    0.07
     âge
    0.07
    rok
    0.07
     convolution
    0.07
    Activations Density 0.008%

    No Known Activations