© 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. 41621
    Prev
    Next
    INDEX
    Explanations

    drought

    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
    cel
    -0.07
    ارج
    -0.07
    ä¸Ĭä¸ĭçıŃ
    -0.07
    çļĦåĪĨ
    -0.07
    reh
    -0.07
     territoriale
    -0.06
    ç£ķ
    -0.06
     rÃło
    -0.06
     procedural
    -0.06
     Dawn
    -0.06
    POSITIVE LOGITS
     drought
    0.11
    å¹²æű
    0.10
     events
    0.08
    æĬĹæű
    0.08
    äºĭ件ä¸Ń
    0.08
    å¼Ĥ常çļĦ
    0.08
    äºĭ件
    0.08
    ürn
    0.08
    EventType
    0.08
    äºĭ件çļĦ
    0.08
    Activations Density 0.041%

    No Known Activations