© 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. 8465
    Prev
    Next
    INDEX
    Explanations

    numbers, quantities, 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
    æł¼æĭīæĸ¯
    -0.07
    æĤ¨çļĦä½įç½®
    -0.07
    æĬµ
    -0.07
    ar
    -0.07
    .TODO
    -0.06
    an
    -0.06
    ç³»
    -0.06
    å¤ļè¾¾
    -0.06
    ipl
    -0.06
    isman
    -0.06
    POSITIVE LOGITS
    rale
    0.08
    Produc
    0.07
    ãģļãģ¤
    0.07
    jured
    0.07
    elev
    0.07
     elev
    0.07
    \Service
    0.07
    åīįãģĭãĤī
    0.07
    ongan
    0.07
    ãģĺãĤģ
    0.07
    Activations Density 0.005%

    No Known Activations