© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3761
    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
    reducers
    -0.21
    noinspection
    -0.21
    .showError
    -0.21
    .AutoScaleDimensions
    -0.20
    }->{
    -0.20
     |/
    -0.20
    ighton
    -0.19
     yans
    -0.19
    姣
    -0.19
     strncpy
    -0.19
    POSITIVE LOGITS
    -scalable
    0.25
    illisecond
    0.25
    ðŁĵIJ
    0.25
    âļĹ
    0.24
    ðŁĵĻ
    0.23
    Sharper
    0.22
    %";↵
    0.21
    åĪ©çĶ¨æĤ¨çļĦ
    0.21
    istring
    0.21
    oldem
    0.20
    Activations Density 0.000%

    No Known Activations