© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 710
    Prev
    Next
    INDEX
    Explanations

    version

    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
    IODevice
    -0.26
     offsetX
    -0.22
     offsetY
    -0.21
     Según
    -0.20
     principalTable
    -0.20
    --)č↵
    -0.20
     btnCancel
    -0.19
     SwiftUI
    -0.19
     xOffset
    -0.18
    æĸĩåĮĸä¼łæĴŃ
    -0.18
    POSITIVE LOGITS
    çīĪæľ¬
    0.59
     version
    0.50
     versions
    0.43
    çīĪ
    0.40
    version
    0.39
     Version
    0.38
    .version
    0.36
    .VERSION
    0.34
    _version
    0.34
    Version
    0.33
    Activations Density 2.498%

    No Known Activations