© 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. 3194
    Prev
    Next
    INDEX
    Explanations

    combined

    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
    鲨
    -0.08
    ampe
    -0.07
    æĿĢ人
    -0.06
    è¯Ħ为
    -0.06
    olie
    -0.06
    æĶ»
    -0.06
    éĩĩçĶ¨çļĦæĺ¯
    -0.06
    yk
    -0.06
    以轻
    -0.06
    ufact
    -0.06
    POSITIVE LOGITS
     combined
    0.14
    combined
    0.14
     Combined
    0.13
    Combined
    0.13
    åIJĪãĤıãģĽ
    0.12
    .concat
    0.12
    åĨįåĬłä¸Ĭ
    0.12
    åĬłä¸Ĭ
    0.11
    åĬłèµ·æĿ¥
    0.10
     plus
    0.10
    Activations Density 0.101%

    No Known Activations