© 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. 4082
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    /MPL
    -0.26
     csak
    -0.24
     lehet
    -0.24
     potrÃł
    -0.24
     elÅij
    -0.23
     Blanc
    -0.22
    apons
    -0.22
    xcf
    -0.21
    LLU
    -0.21
     minden
    -0.21
    POSITIVE LOGITS
    orgia
    0.24
    æŀ¶åŃIJ
    0.21
     Fur
    0.21
    rylic
    0.19
     plates
    0.19
    armacy
    0.19
    inté
    0.18
    çķ´
    0.18
     componentDidUpdate
    0.18
    BOTTOM
    0.18
    Activations Density 0.001%

    No Known Activations