© 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. 283
    Prev
    Next
    INDEX
    Explanations

    technical or business

    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
    orgeous
    -0.26
    <=(
    -0.25
    ÑīиÑĤ
    -0.23
    ponge
    -0.23
    ptrdiff
    -0.23
    buat
    -0.22
    )))));↵
    -0.22
    antiago
    -0.22
     ?>"↵
    -0.21
    otify
    -0.21
    POSITIVE LOGITS
    çļĦç¼ĺ
    0.22
    ushman
    0.22
    âĸį
    0.21
     giochi
    0.20
    .scalablytyped
    0.20
    é¾Ĭ
    0.20
     addCriterion
    0.20
     UIStoryboard
    0.19
     ragazzi
    0.19
    çļĦç«ŀäºī
    0.19
    Activations Density 5.056%

    No Known Activations