© 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. 61056
    Prev
    Next
    INDEX
    Explanations

    magnification and microscopy

    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
    inja
    -0.07
    æŶéĹ´çĤ¹
    -0.07
    åĵį
    -0.07
    Fuel
    -0.06
    èĵĦæ°´
    -0.06
     distributions
    -0.06
    çİĦæѦ
    -0.06
     Generator
    -0.06
    _self
    -0.06
    ruz
    -0.06
    POSITIVE LOGITS
     microscope
    0.13
    æĺ¾å¾®éķľ
    0.13
    æĺ¾å¾®
    0.12
    æĶ¾å¤§éķľ
    0.11
     microscopy
    0.10
    åĢįæķ°
    0.10
    æĶ¾å¤§
    0.10
     magn
    0.10
     lenses
    0.10
    æłĩæľ¬
    0.09
    Activations Density 0.016%

    No Known Activations