© 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. 1019
    Prev
    Next
    INDEX
    Explanations

    years

    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
     “
    -0.24
     once
    -0.21
    elerik
    -0.21
    .
    -0.21
    Âł
    -0.21
    celand
    -0.20
     apt
    -0.20
    ornings
    -0.20
    akespeare
    -0.19
    ,
    -0.19
    POSITIVE LOGITS
    ä¸Ģèĩ´å¥½è¯Ħ
    0.29
    âĦī
    0.24
    icions
    0.23
    æĢ§ä»·
    0.23
    缸åħ³æĸ°éĹ»
    0.23
     (~(
    0.22
    loggedin
    0.22
     .↵↵↵↵
    0.22
     (*((
    0.22
     "\",
    0.21
    Activations Density 1.034%

    No Known Activations