© 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. 4202
    Prev
    Next
    INDEX
    Explanations

    assign

    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
    è¿Ľè¡Į
    -0.23
    meye
    -0.21
    alyzed
    -0.20
    è§Ħéģ¿
    -0.20
    -caret
    -0.19
     undergo
    -0.19
    åı¨
    -0.19
    é¢Ĩåıĸ
    -0.19
    uchos
    -0.19
    argins
    -0.18
    POSITIVE LOGITS
    иÑĢÑĥем
    0.22
     assign
    0.22
    ä¸į让
    0.21
    溦
    0.20
     "','
    0.20
    IOS
    0.20
    让
    0.20
    èµĭäºĪ
    0.20
    ä¹Łè®©
    0.20
    assign
    0.20
    Activations Density 0.631%

    No Known Activations