© 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. 556
    Prev
    Next
    INDEX
    Explanations

    court

    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
    icopt
    -0.22
    Ľå»º
    -0.21
     LinearGradient
    -0.19
        	č↵
    -0.19
    apsible
    -0.19
    ĵåIJį
    -0.19
     Rider
    -0.18
    apiro
    -0.18
    ynet
    -0.18
    letal
    -0.18
    POSITIVE LOGITS
    åĨ³å®ļ
    0.28
    inerary
    0.24
     deciding
    0.24
     decision
    0.23
    åıĹçIJĨ
    0.23
    Decision
    0.23
     decisions
    0.23
    审çIJĨ
    0.23
     ruling
    0.22
     decide
    0.22
    Activations Density 0.998%

    No Known Activations