© 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. 4107
    Prev
    Next
    INDEX
    Explanations

    completing tasks

    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
     cornerback
    -0.25
    lasting
    -0.21
    ADER
    -0.21
    ä¹Ĵä¹ĵ
    -0.21
    ActiveSheet
    -0.21
    Erreur
    -0.20
    BaseContext
    -0.20
    ="'.
    -0.20
     ÄijÃŃch
    -0.19
    otte
    -0.19
    POSITIVE LOGITS
    åѦä¸ļ
    0.27
    bove
    0.27
     migli
    0.23
     caratter
    0.21
    omaly
    0.21
    使åij½
    0.21
    å®ĮæĪIJäºĨ
    0.21
    ä¸įäºĨ
    0.21
    cestor
    0.20
     incomplete
    0.20
    Activations Density 0.154%

    No Known Activations