© 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. 60893
    Prev
    Next
    INDEX
    Explanations

    connections and relations

    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
    大夫
    -0.07
    \Resource
    -0.07
    大å®ī
    -0.07
    çĽ¸ä¼¼æĸĩçĮ®
    -0.07
    icho
    -0.07
    argomento
    -0.07
    对ä»ĸ们çļĦ
    -0.07
    åı°
    -0.06
    ä½ĵè´¨
    -0.06
    .dds
    -0.06
    POSITIVE LOGITS
    è¿ŀæİ¥
    0.08
    ä¸Ĭä¸ĢæĿ¡
    0.08
     verbindet
    0.07
    åı¦ä¸Ģ个
    0.07
    connecting
    0.07
     Other
    0.07
    å´İ
    0.07
     ná»iji
    0.07
    è¿ŀæİ¥åĪ°
    0.07
    éĢļå¾Ģ
    0.07
    Activations Density 0.009%

    No Known Activations