© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2087
    Prev
    Next
    INDEX
    Explanations

    fluid dynamics

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vous
    -0.23
    ={!
    -0.22
     onKeyDown
    -0.20
    llx
    -0.20
    reland
    -0.19
    esto
    -0.19
    Extras
    -0.19
    codec
    -0.19
    :'.$
    -0.18
    .Setter
    -0.18
    POSITIVE LOGITS
     Reynolds
    0.24
     Proud
    0.22
     turbulence
    0.21
    ç´Ĭ
    0.20
     fluids
    0.20
     stagn
    0.19
     turbulent
    0.19
     deployments
    0.19
    assage
    0.19
     Fluid
    0.19
    Activations Density 0.249%

    No Known Activations