© 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. 26829
    Prev
    Next
    INDEX
    Explanations

    explains a concept, answered, tried code

    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
    æĬķèµĦæĪĸ
    -0.10
    æľīä¸ĢäºĽ
    -0.09
    缴æİ¥æĪĸ
    -0.09
    æĸĩ件æĪĸ
    -0.08
    æŁIJäºĽ
    -0.08
    æĪĸ被
    -0.08
    åģļäºĽ
    -0.08
     somehow
    -0.07
    DOMNode
    -0.07
    好çľĭçļĦ
    -0.07
    POSITIVE LOGITS
    解éĩĬäºĨ
    0.07
     multiple
    0.07
    both
    0.07
     both
    0.07
    å¤ļ个
    0.07
    详ç»Ĩä»ĭç»įäºĨ
    0.07
    说æĺİäºĨ
    0.07
     explains
    0.07
     discusses
    0.07
    ç¿Ķ
    0.07
    Activations Density 0.007%

    No Known Activations