© 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. 63920
    Prev
    Next
    INDEX
    Explanations

    first derivative of

    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
    ToDevice
    -0.08
    ä¸Ĭä¹ĺ
    -0.08
    å°½èĩªå·±
    -0.07
    笳
    -0.07
    ehe
    -0.07
    idon
    -0.07
    æī¿æĭħçļĦ
    -0.07
    Xã
    -0.07
    뢰
    -0.07
    ä¸İä¼ļ人åijĺ
    -0.07
    POSITIVE LOGITS
    åıįé¦Ī
    0.08
     feedback
    0.07
    itol
    0.07
    å¤įåIJĪ
    0.06
    çIJ¢ç£¨
    0.06
    åºĩ
    0.06
     Cultur
    0.06
     Slo
    0.06
    ommel
    0.06
     Feedback
    0.06
    Activations Density 0.003%

    No Known Activations