© 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. 2928
    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
    egis
    -0.26
    ');↵↵↵↵
    -0.26
    swer
    -0.25
    bsolute
    -0.25
    .twig
    -0.25
    osemite
    -0.24
    imbus
    -0.24
     Interracial
    -0.24
    oubted
    -0.23
    oproject
    -0.23
    POSITIVE LOGITS
     decltype
    0.23
    ç§ģç«ĭ
    0.21
    å¸Ĥå§Ķ常å§Ķ
    0.20
    èĮĶ
    0.19
    ä¸įéĹ´
    0.19
    .startActivity
    0.19
    isel
    0.19
    åĶ¢
    0.18
    èĩ¾
    0.18
    «
    0.18
    Activations Density 0.000%

    No Known Activations