© 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. 23596
    Prev
    Next
    INDEX
    Explanations

    fluid and related 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
    åıĬè¦ģæ±Ĥ
    -0.08
    ä¹ħä¹ħ
    -0.08
    ForObject
    -0.08
    ä¹ħä¹ĭ
    -0.07
    /original
    -0.07
    ulg
    -0.07
    kung
    -0.07
     lẻ
    -0.07
    å«£çĦ¶
    -0.07
     белÑĮ
    -0.07
    POSITIVE LOGITS
     fluid
    0.09
    Fluid
    0.09
    -fluid
    0.08
     Fluid
    0.08
    fluid
    0.08
    æŁĶ软
    0.08
     fluids
    0.08
    è¿IJåĬ¨ä¸Ń
    0.08
    æŁĶæĢ§
    0.08
    æµģä½ĵ
    0.07
    Activations Density 0.016%

    No Known Activations