© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 110
    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
    *sp
    -0.34
    -mf
    -0.32
    icions
    -0.30
    swire
    -0.28
    <small
    -0.28
    byss
    -0.28
    ;break
    -0.28
    oins
    -0.27
    %"><
    -0.27
    -Cs
    -0.26
    POSITIVE LOGITS
     stil
    0.23
    etro
    0.21
    å·¡èĪª
    0.20
     concern
    0.19
    åIJ«
    0.19
     segment
    0.19
     UnityEditor
    0.19
    ,
    0.19
    ter
    0.19
    éĻĽä¸ĭ
    0.19
    Activations Density 0.001%

    No Known Activations