© 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. 51481
    Prev
    Next
    INDEX
    Explanations

    viscoelastic properties

    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
    åıĹç²¾åįµ
    -0.09
    mers
    -0.07
    rimi
    -0.07
    faf
    -0.06
     locate
    -0.06
     loc
    -0.06
     cerc
    -0.06
    fan
    -0.06
    çĪ¶å¥³
    -0.06
    اÙĤ
    -0.06
    POSITIVE LOGITS
    没æľīæŶéĹ´
    0.09
     response
    0.09
     responses
    0.09
    åĵįåºĶ
    0.09
     Response
    0.08
    æŶéĹ´çļĦ
    0.08
    éļıçĿĢæŶéĹ´çļĦ
    0.08
    elastic
    0.08
    responses
    0.08
    åħ·ä½ĵæŶéĹ´
    0.08
    Activations Density 0.008%

    No Known Activations