© 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. 2977
    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
    buat
    -0.23
     CONSEQUENTIAL
    -0.22
    åIJįåĪĹåīį
    -0.22
    æݨåĩºçļĦ
    -0.20
    ecided
    -0.20
    ︱
    -0.19
    licas
    -0.19
    è¿ĻæĶ¯
    -0.19
    >tag
    -0.19
    åIJĿ
    -0.19
    POSITIVE LOGITS
    ekyll
    0.22
     tud
    0.21
     valueForKey
    0.21
    ("$.
    0.20
    irt
    0.19
    ircraft
    0.18
    _CLR
    0.18
     domest
    0.18
    Detalle
    0.18
    æīĢæľīæĥħèĬĤ
    0.18
    Activations Density 0.000%

    No Known Activations