© 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. 17349
    Prev
    Next
    INDEX
    Explanations

    sequences of letters followed by punctuation

    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
    ukat
    -0.07
    ftar
    -0.07
    åĪ·åĪ·
    -0.07
    ANTE
    -0.06
    ê³¼ìĿĺ
    -0.06
    mez
    -0.06
    tring
    -0.06
    uangan
    -0.06
    atee
    -0.06
    सà¥įया
    -0.06
    POSITIVE LOGITS
     respectively
    0.09
    åIJĦèĩª
    0.09
    åIJĦèĩªçļĦ
    0.09
    åĪĨåĪ«
    0.08
    å½¼æѤ
    0.08
    ayet
    0.08
    ãģ¨ãĤĤãģ«
    0.07
    ãģĿãĤĮãģŀãĤĮ
    0.07
     alike
    0.07
    bsites
    0.07
    Activations Density 0.034%

    No Known Activations