© 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. 4208
    Prev
    Next
    INDEX
    Explanations

    ethics review board

    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
    lijah
    -0.23
    .epam
    -0.20
    derabad
    -0.20
    berra
    -0.20
    ç¾İåªĴ
    -0.20
    adge
    -0.19
    ://%
    -0.19
    okus
    -0.19
    rompt
    -0.19
    AZY
    -0.19
    POSITIVE LOGITS
     komment
    0.22
    благо
    0.22
    /Internal
    0.21
     beÄŁen
    0.21
     controlId
    0.20
     zob
    0.20
    -gradient
    0.20
     näm
    0.20
     DISCLAIMS
    0.19
    cop
    0.19
    Activations Density 0.009%

    No Known Activations