© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61868
    Prev
    Next
    INDEX
    Explanations

    teams, countries, and proper nouns

    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
    —which
    -0.08
    =view
    -0.08
    以åıĬå¦Ĥä½ķ
    -0.08
    {text
    -0.08
     '",
    -0.07
    åĬŀ好
    -0.07
    ...',
    -0.07
    æĤ¨åı¯èĥ½
    -0.07
    izo
    -0.07
     ↵↵↵↵↵
    -0.07
    POSITIVE LOGITS
    à¹Īาย
    0.08
     |
    0.07
    ÑĢÑĬ
    0.07
    話
    0.07
    oke
    0.06
    IKE
    0.06
     /
    0.06
     ìŀĪìĿĮ
    0.06
    ç¥ĸæ¯į
    0.06
    oph
    0.06
    Activations Density 0.978%

    No Known Activations