© 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. 29494
    Prev
    Next
    INDEX
    Explanations

    names, places, or titles

    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
    æī¾æĪ¿
    -0.07
    çİ®
    -0.07
    yclic
    -0.06
    μή
    -0.06
    åħ¶éģĵ
    -0.06
    jala
    -0.06
    acci
    -0.06
    /fixtures
    -0.06
    shots
    -0.06
     CP
    -0.06
    POSITIVE LOGITS
    -turned
    0.16
    转åĮĸ为
    0.16
    转åıĺ为
    0.15
    转åĮĸæĪIJ
    0.15
    转æį¢ä¸º
    0.14
    åįĩ级为
    0.13
     converted
    0.13
    转æį¢æĪIJ
    0.13
    åıĺæĪIJ
    0.13
     تبدÛĮÙĦ
    0.13
    Activations Density 0.416%

    No Known Activations