© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3713
    Prev
    Next
    INDEX
    Explanations

    technical code snippets

    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
    家éĥ½çŁ¥éģĵ
    -0.26
    SharedPtr
    -0.25
    -scalable
    -0.24
    ponce
    -0.24
    achuset
    -0.23
     Bathroom
    -0.22
    ÙĪضÙĪع
    -0.22
    .chomp
    -0.21
     sok
    -0.21
    onomies
    -0.21
    POSITIVE LOGITS
    thinkable
    0.23
     de
    0.20
    代
    0.20
    minent
    0.19
    ologne
    0.19
    ç«£
    0.19
    ürnberg
    0.19
    åij¤
    0.19
    .TestTools
    0.19
     Dems
    0.19
    Activations Density 0.424%

    No Known Activations