© 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. 3875
    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
    :maj
    -0.31
    [".
    -0.25
    ifestyles
    -0.24
    áIJī
    -0.24
    iferay
    -0.24
    .Millisecond
    -0.23
    ATUS
    -0.22
    __,__
    -0.22
    âļĹ
    -0.22
    /MPL
    -0.21
    POSITIVE LOGITS
     Territories
    0.19
     mascara
    0.19
    addtogroup
    0.19
    layer
    0.19
    æľĪæľ«
    0.18
    _documento
    0.18
     stom
    0.18
    flush
    0.18
    mock
    0.18
     inflamm
    0.18
    Activations Density 0.000%

    No Known Activations