© 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. 19787
    Prev
    Next
    INDEX
    Explanations

    continuity equation and density

    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
    лÑij
    -0.08
    heb
    -0.08
    弯弯
    -0.08
    liers
    -0.08
    ãģĭãģĽ
    -0.08
     xá»ī
    -0.08
    ijľ
    -0.08
    /boot
    -0.07
    ANGLES
    -0.07
    BootApplication
    -0.07
    POSITIVE LOGITS
     density
    0.11
    å¯Ĩ度
    0.10
     flow
    0.10
     Density
    0.09
    flow
    0.09
    density
    0.09
    -density
    0.08
    æµģéĢŁ
    0.08
     densities
    0.08
     Flow
    0.08
    Activations Density 0.001%

    No Known Activations