© 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. 17771
    Prev
    Next
    INDEX
    Explanations

    comparison of sizes

    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
    bracht
    -0.07
    rese
    -0.07
    å¸ļ
    -0.07
    çıĬ
    -0.07
    ç²±
    -0.07
    trys
    -0.07
    vania
    -0.07
     parall
    -0.07
    çĪ±æĺ¯
    -0.07
    plit
    -0.07
    POSITIVE LOGITS
    ä¸ĭä¸Ģ级
    0.12
     ÙĪÙĩÙĥذا
    0.11
    ä¾Ŀ次
    0.10
    éĢIJ级
    0.10
    ä¸Ĭä¸Ģå±Ĥ
    0.10
    å±Ĥå±Ĥ
    0.09
    çĦ¶åIJİæĺ¯
    0.09
    åħ¶æ¬¡
    0.08
    ä¸ī级
    0.08
    ä¸ĭä¸Ģ个
    0.08
    Activations Density 0.153%

    No Known Activations