© 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. 43191
    Prev
    Next
    INDEX
    Explanations

    bank holiday or school

    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
    潺
    -0.08
    Resolved
    -0.07
    ($)
    -0.07
    anty
    -0.07
    åĪ¶å®ľ
    -0.07
    orz
    -0.07
    cule
    -0.07
    xil
    -0.07
    ç²¹
    -0.07
    ctl
    -0.06
    POSITIVE LOGITS
    åĨįåĬłä¸Ĭ
    0.09
    åĬłä¸Ĭ
    0.07
    æĪijçļĦæīĭ
    0.07
    auc
    0.06
    åĨįåĬł
    0.06
    niec
    0.06
     Stevenson
    0.06
    Benchmark
    0.06
    è¿ĺæĺ¯æ¯Ķè¾ĥ
    0.06
    ìĨIJ
    0.06
    Activations Density 0.002%

    No Known Activations