© 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. 1213
    Prev
    Next
    INDEX
    Explanations

    optical system or lens

    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
    é²ľæ´»
    -0.09
    èĦīæIJı
    -0.08
    骨é«ĵ
    -0.08
    çĶµç½ij
    -0.08
    åĬ¨åijĺ
    -0.07
     heartbeat
    -0.07
    gar
    -0.07
    gara
    -0.07
    leve
    -0.07
    æ¸ĹéĢı
    -0.07
    POSITIVE LOGITS
    åħīåѦ
    0.13
     optical
    0.13
     Optical
    0.12
     optics
    0.12
    磫æŃ£
    0.11
     опÑĤи
    0.10
     lenses
    0.10
    éķľçīĩ
    0.10
     lens
    0.10
    çĦ¦è·Ŀ
    0.09
    Activations Density 0.096%

    No Known Activations