© 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. 4137
    Prev
    Next
    INDEX
    Explanations

    code symbols

    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
    åĶĨ
    -0.19
    illisecond
    -0.19
    ih
    -0.19
    å¼Ģå¥ĸç»ĵæŀľ
    -0.18
    SearchTree
    -0.18
    ERRY
    -0.18
     pathMatch
    -0.18
     Zap
    -0.18
    /bash
    -0.18
    ughters
    -0.18
    POSITIVE LOGITS
    IFS
    0.26
     ula
    0.23
    nection
    0.23
    ("\(
    0.21
    çİ°
    0.20
     Según
    0.20
    legates
    0.19
     {?>↵
    0.19
     RoundedRectangle
    0.18
    çĸĹ
    0.18
    Activations Density 0.151%

    No Known Activations