© 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. 2028
    Prev
    Next
    INDEX
    Explanations

    Solve equations

    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
     Ãģrea
    -0.20
     ActionTypes
    -0.20
    -wow
    -0.19
    âĨ¾
    -0.19
    åħħ足
    -0.19
    -initialized
    -0.19
     troch
    -0.19
    olis
    -0.19
    æīĵè¿Ľ
    -0.18
     hurd
    -0.18
    POSITIVE LOGITS
     whiteColor
    0.23
     blackColor
    0.23
    åŁļ
    0.21
    hế
    0.21
    á¼Ķ
    0.20
    á¼Ħ
    0.20
    imageView
    0.20
    ⩽
    0.20
    ãİĿ
    0.19
     (*)(
    0.19
    Activations Density 0.063%

    No Known Activations