© 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. 2854
    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
    uxtap
    -0.26
    ();?>
    -0.22
     mainBundle
    -0.22
    зÑĭк
    -0.22
     bindActionCreators
    -0.21
    ".↵↵↵↵
    -0.21
     italiane
    -0.21
     ['./
    -0.20
    chor
    -0.20
    _RSA
    -0.20
    POSITIVE LOGITS
    .fromRGBO
    0.21
    æŁ¥çľĭ详æĥħ
    0.20
     numberWith
    0.19
    idar
    0.19
    uite
    0.19
    .Variable
    0.18
    OrDefault
    0.18
    amework
    0.18
    ows
    0.18
    rac
    0.18
    Activations Density 0.000%

    No Known Activations