© 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. 1932
    Prev
    Next
    INDEX
    Explanations

    code and text fragments

    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
    hibited
    -0.20
    ocrats
    -0.20
    èĩ´ãģĹãģ¾ãģĻ
    -0.20
    iente
    -0.19
    onent
    -0.19
     Murphy
    -0.19
    åĪ«
    -0.18
     S
    -0.18
     Erf
    -0.18
    POSITIVE LOGITS
     Decompiled
    0.23
     Interracial
    0.23
    **/↵↵
    0.21
     fkk
    0.21
     WHETHER
    0.20
    arendra
    0.20
    :"#
    0.20
    .moveToNext
    0.20
    æĦĽæĥħ
    0.20
    ourd
    0.20
    Activations Density 0.002%

    No Known Activations