© 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. 1643
    Prev
    Next
    INDEX
    Explanations

    technical programming terms

    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
     èĩªåĬ¨çĶŁæĪIJ
    -0.24
    pollo
    -0.21
    ppelin
    -0.21
    omite
    -0.19
    USART
    -0.19
    âļĹ
    -0.19
     Wallace
    -0.19
     showc
    -0.18
     )}↵↵
    -0.18
    ,__
    -0.18
    POSITIVE LOGITS
    HideInInspector
    0.24
     AndAlso
    0.23
    &action
    0.21
    ulfilled
    0.21
    OCUS
    0.20
    ERIC
    0.20
    Animating
    0.20
     ofApp
    0.20
    __);
    0.20
     Cru
    0.20
    Activations Density 4.332%

    No Known Activations