© 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. 2591
    Prev
    Next
    INDEX
    Explanations

    shallow, superficial

    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
    æĹłåij³
    -0.09
    åĨ·æ·¡
    -0.08
    æĭĵ
    -0.08
    æ·±éĤĥ
    -0.08
    æĹłè¨Ģ
    -0.07
    menes
    -0.07
    æ·±æ²ī
    -0.07
    严èĤĥ
    -0.07
    山大
    -0.07
    itava
    -0.07
    POSITIVE LOGITS
    æµħ
    0.11
    æ·º
    0.10
    表å±Ĥ
    0.09
     shallow
    0.09
    軽ãģĦ
    0.08
    è¾ĥè½»
    0.08
    æµħæµħ
    0.08
     superficial
    0.08
     ê°Ģë²¼
    0.08
    å¤ĸåIJij
    0.08
    Activations Density 0.516%

    No Known Activations