© 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. 4183
    Prev
    Next
    INDEX
    Explanations

    foreign characters

    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
    åľ¨çº¿åĴ¨è¯¢
    -0.29
    éĥ½æľīèĩªå·±
    -0.25
    conexao
    -0.23
    æĭľå¸ĪåѦ
    -0.23
    æľīæľŁå¾Ĵ
    -0.21
    ilmiÅŁ
    -0.21
    eworthy
    -0.21
    éĶĵ
    -0.21
    æĻ°
    -0.20
    áIJī
    -0.20
    POSITIVE LOGITS
     burge
    0.23
     svo
    0.21
    avigate
    0.21
    æ·»
    0.20
    æĥ¬
    0.19
    yped
    0.19
    Û
    0.19
     embar
    0.19
     Clintons
    0.18
    resar
    0.18
    Activations Density 0.034%

    No Known Activations