© 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. 21389
    Prev
    Next
    INDEX
    Explanations

    Pennsylvania placenames

    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
    )':
    -0.08
    åĩºèī²
    -0.07
     (![
    -0.07
    çī¹åĪ«æĺ¯åľ¨
    -0.06
    å°¤åħ¶æĺ¯åľ¨
    -0.06
    à§įম
    -0.06
     soal
    -0.06
     semej
    -0.06
    EIC
    -0.06
    cts
    -0.06
    POSITIVE LOGITS
    亦çĦ¶
    0.07
    以æѤ
    0.07
     appunto
    0.07
    adden
    0.07
    telen
    0.07
    ean
    0.07
    æĺ¯è¿Ļæł·çļĦ
    0.06
    以ä¸Ĭæĺ¯
    0.06
    àºļ
    0.06
    à®ŀ
    0.06
    Activations Density 0.114%

    No Known Activations