© 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. 3065
    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
    âļĹ
    -0.25
    .FlatAppearance
    -0.22
    %;"
    -0.22
    %;">
    -0.21
    %"><
    -0.21
     Bashar
    -0.21
    .UTC
    -0.20
    )(*
    -0.20
    Mathf
    -0.19
    âĮĤ
    -0.19
    POSITIVE LOGITS
    ä¸ĩåħ¬éĩĮ
    0.21
    åŁ
    0.20
    wand
    0.19
    aeda
    0.19
    Cake
    0.18
    ÙĤ
    0.18
    USE
    0.18
    _Texture
    0.18
     Forge
    0.18
    榻
    0.18
    Activations Density 0.000%

    No Known Activations