© 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. 8581
    Prev
    Next
    INDEX
    Explanations

    feudalism, knights, charter, medieval, lords

    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
    abora
    -0.10
    ZION
    -0.09
    åĽŃè·¯
    -0.09
     Edison
    -0.09
     canned
    -0.08
    iblio
    -0.08
     desi
    -0.08
     Gandhi
    -0.08
    åħijç¾İåħĥ
    -0.08
    岸
    -0.08
    POSITIVE LOGITS
     medieval
    0.15
     Medieval
    0.14
     knights
    0.11
     feudal
    0.09
     lords
    0.09
    é¢Ĩ主
    0.08
     Gothic
    0.08
     guild
    0.08
     castle
    0.08
     knight
    0.08
    Activations Density 0.430%

    No Known Activations