© 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. 26207
    Prev
    Next
    INDEX
    Explanations

    code/program identifiers

    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
    aglio
    -0.07
    enty
    -0.07
    ä¸īé«ĺ
    -0.07
    ζί
    -0.07
    å¾
    -0.07
    лад
    -0.07
    大峡谷
    -0.07
    ander
    -0.06
    ong
    -0.06
    å¿ĥæĦ¿
    -0.06
    POSITIVE LOGITS
    æ´Ľå¤«
    0.07
    .kr
    0.07
    æĺİæĺİæĺ¯
    0.06
     ÙĨØ®
    0.06
    æĿ¥ä¹ĭ
    0.06
    èijĽ
    0.06
    ernes
    0.06
     Fons
    0.06
    ä¹ĭç¥ŀ
    0.06
    anson
    0.06
    Activations Density 0.051%

    No Known Activations