© 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. 23204
    Prev
    Next
    INDEX
    Explanations

    energy, power, or charge transfer

    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¸ŃçĶŁ
    -0.07
    éħįåIJĪ
    -0.07
    ãģ«ãģĭ
    -0.06
    ä¸ŃæĹ¥
    -0.06
    Ïħν
    -0.06
    éľ²åĩºä¸Ģ
    -0.06
     anything
    -0.06
    à¸ŀาà¸Ļ
    -0.06
     nada
    -0.06
    天æĺİ
    -0.06
    POSITIVE LOGITS
     transfer
    0.10
    transfer
    0.10
    ä»İéĤ£
    0.10
    主è¦ģä»İ
    0.10
    转移åĪ°
    0.10
    .appendTo
    0.09
    转移
    0.09
     transferred
    0.09
    ä»İè¿Ļ个
    0.09
    -transfer
    0.09
    Activations Density 0.417%

    No Known Activations