© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4122
    Prev
    Next
    INDEX
    Explanations

    frequency/commonality

    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
    Negative Logits
     (){
    -0.21
    \Collections
    -0.21
    Ŀå§ĭ
    -0.20
     Según
    -0.19
    ária
    -0.19
     fkk
    -0.19
    ipsoid
    -0.19
    uliar
    -0.19
    pta
    -0.18
    /bower
    -0.18
    POSITIVE LOGITS
     usually
    0.62
     typically
    0.60
    éĢļ常
    0.55
    éĢļ常æĺ¯
    0.52
    usually
    0.51
     Typically
    0.49
     Usually
    0.48
     often
    0.48
    ä¸ĢèĪ¬æĺ¯
    0.47
    æľīçļĦ
    0.44
    Activations Density 0.988%

    No Known Activations