© 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. 46073
    Prev
    Next
    INDEX
    Explanations

    viscosity

    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
    çĪ¶å¥³
    -0.07
     xmlns
    -0.07
     rech
    -0.07
    强åħī
    -0.07
    çĶµéĩı
    -0.07
     recl
    -0.07
    è¡¥éĴĻ
    -0.06
    emand
    -0.06
    çħ§å°Ħ
    -0.06
     اÙĦÙĩر
    -0.06
    POSITIVE LOGITS
     viscosity
    0.13
    ç²ĺ度
    0.12
    ç²ĺ
    0.12
    ç²ĺæĢ§
    0.10
    é»ı
    0.10
    ç²ĺ稳
    0.10
     visc
    0.09
    æµģä½ĵ
    0.09
    æµģåĬ¨æĢ§
    0.08
    æµģæ·Į
    0.08
    Activations Density 0.002%

    No Known Activations