© 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. 4036
    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
    ,cp
    -0.23
    }/#{
    -0.22
    quential
    -0.22
    \uD
    -0.22
    istributor
    -0.22
    nio
    -0.21
     )↵↵↵↵↵↵↵↵
    -0.20
    lijah
    -0.20
    nas
    -0.20
    âĵĴ
    -0.20
    POSITIVE LOGITS
     algu
    0.24
    .MouseAdapter
    0.22
    åĬŁ
    0.21
     regard
    0.20
     repmat
    0.20
    èĨ³
    0.19
    tons
    0.19
     masturbating
    0.19
     today
    0.19
    ffd
    0.19
    Activations Density 0.000%

    No Known Activations