© 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. 63095
    Prev
    Next
    INDEX
    Explanations

    second, third, fourth

    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
    人人
    -0.07
    amat
    -0.07
    é©
    -0.06
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    -0.06
    otel
    -0.06
     moc
    -0.06
    ä¸īåĽĽ
    -0.06
     Firstly
    -0.06
    l
    -0.06
    lah
    -0.06
    POSITIVE LOGITS
    !!:
    0.09
    tle
    0.08
    stö
    0.08
    ä¾ĭåŃIJ
    0.07
    åı¯æľĽ
    0.07
    czy
    0.07
    ç»ĵæŀľè¡¨æĺİ
    0.07
    ä¸ĵ家æĮĩåĩº
    0.07
    æ½°
    0.07
    catch
    0.07
    Activations Density 0.002%

    No Known Activations