© 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. 2543
    Prev
    Next
    INDEX
    Explanations

    is/being followed by adjective

    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
    ä¸įäºĨäºĨ
    -0.07
    ä¿Ń
    -0.07
    å¦Ĥä¸Ģ
    -0.07
    å¦Ĥçİī
    -0.07
    orget
    -0.07
    ä¹ŁæľīæīĢ
    -0.07
    Ñİд
    -0.07
    ä¸įçŁ¥éģĵçļĦ
    -0.07
    ä¸Ģå®ļæĺ¯
    -0.07
    ä¸Ģæī¹
    -0.07
    POSITIVE LOGITS
    å±ŀäºİ
    0.07
    屬æĸ¼
    0.07
    )&&(
    0.07
     notoriously
    0.07
     btw
    0.07
    )&&
    0.07
     certes
    0.07
    æĹ¢æĺ¯
    0.06
    lder
    0.06
    _HAS
    0.06
    Activations Density 0.061%

    No Known Activations