© 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. 26415
    Prev
    Next
    INDEX
    Explanations

    jet propulsion, fluid flow, mixing, velocity

    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
     ticks
    -0.09
     tick
    -0.08
    ä¼ijçľł
    -0.07
     ticking
    -0.07
     scratch
    -0.07
    èĪªæµ·
    -0.07
    履约
    -0.07
     trem
    -0.07
    累积
    -0.06
    scratch
    -0.06
    POSITIVE LOGITS
    åĪĨæµģ
    0.12
    æµģéĢŁ
    0.11
     inlet
    0.11
     outlet
    0.11
     downstream
    0.10
    æµģéĩı
    0.10
     exit
    0.10
     flow
    0.09
    åĩºåı£
    0.09
    åĩºåı£çļĦ
    0.09
    Activations Density 0.050%

    No Known Activations