© 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. 49171
    Prev
    Next
    INDEX
    Explanations

    numbers and counts

    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
    è¦ģä¹Ī
    -0.08
     zwar
    -0.08
     EITHER
    -0.06
     entweder
    -0.06
    åĽºçĦ¶
    -0.06
    è¦ģä¹Īæĺ¯
    -0.06
    起家
    -0.06
    é¢ĵ
    -0.06
    åħĪæĺ¯
    -0.06
    åħ³æ³¨åħ¬ä¼Ĺåı·
    -0.06
    POSITIVE LOGITS
     depending
    0.08
     sempat
    0.08
     thereof
    0.08
     ones
    0.08
     daarvan
    0.07
    ä¸į计
    0.07
    æĽ´ä½³
    0.07
    åįĹé£İ
    0.07
    æĽ´ä¸įä¼ļ
    0.07
     thereafter
    0.07
    Activations Density 0.191%

    No Known Activations