© 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. 43910
    Prev
    Next
    INDEX
    Explanations

    lithography, semiconductor, gate, connect, resist

    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
    罡
    -0.07
    建ç«Ļ
    -0.07
    زÙĨ
    -0.07
    èģĶç½ij
    -0.06
    对çĶŁæ´»
    -0.06
    æĪªåıĸ
    -0.06
    aise
    -0.06
    æŀ¶åŃIJ
    -0.06
     FLAC
    -0.06
     chol
    -0.06
    POSITIVE LOGITS
    æĻ¶åľĨ
    0.10
    åĪ¶ç¨ĭ
    0.10
     manufact
    0.09
    åĻ¨ä»¶
    0.09
     Semiconductor
    0.09
    hattan
    0.09
     semiconductor
    0.08
     aggress
    0.08
    设计åħ¬åı¸
    0.08
     fabs
    0.08
    Activations Density 0.419%

    No Known Activations