© 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. 63480
    Prev
    Next
    INDEX
    Explanations

    historical birth or death years

    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
    åıĺçĶµç«Ļ
    -0.08
     subclasses
    -0.07
    subclass
    -0.07
    åĸľé©¬æĭīéĽħ
    -0.07
    urato
    -0.07
    ophon
    -0.07
    åѵ
    -0.07
     Baghd
    -0.07
    秦å²Ń
    -0.07
     ÙĥÙĩرب
    -0.07
    POSITIVE LOGITS
    æĺİæľĿ
    0.09
    æĺİ代
    0.09
     Protestant
    0.08
    大æĺİ
    0.08
     Flem
    0.08
    æľ±åħĥçĴĭ
    0.07
    oon
    0.07
     Tud
    0.07
    atio
    0.07
     VOC
    0.07
    Activations Density 0.144%

    No Known Activations