© 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. 11290
    Prev
    Next
    INDEX
    Explanations

    quality, credit, coverage, DNA

    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
    abis
    -0.08
    太大äºĨ
    -0.08
    ä»»ä½ķè´¹çĶ¨
    -0.08
    å¼ı设计
    -0.08
     maxHeight
    -0.08
    bih
    -0.08
    Ø°Ùģ
    -0.07
    ниÑĨ
    -0.07
    _finalize
    -0.07
    ä¸įæĸŃå¢ŀéķ¿
    -0.07
    POSITIVE LOGITS
    çļĦ好åĿı
    0.13
    好åĿı
    0.11
    çĬ¶åĨµ
    0.10
     quality
    0.10
     poor
    0.09
    ä¸įä½³
    0.09
    è¶Ĭ好
    0.09
    æľĢå·®
    0.09
    è´¨éĩı
    0.08
     deterior
    0.08
    Activations Density 0.147%

    No Known Activations