© 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. 2280
    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
     either
    -0.21
    prevState
    -0.20
     trap
    -0.20
    çłĶ究æīĢ
    -0.20
    涨
    -0.19
    Refs
    -0.19
     UnityEditor
    -0.19
    precated
    -0.19
    åįī
    -0.18
     subrange
    -0.18
    POSITIVE LOGITS
    );}↵↵
    0.26
    aeda
    0.24
    "<?
    0.24
    #aa
    0.24
    ^K
    0.23
    "';
    0.23
    )];
    0.23
    __;
    0.22
    OCUS
    0.22
    cade
    0.22
    Activations Density 0.001%

    No Known Activations