© 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. 3560
    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
    aukee
    -0.22
     jel
    -0.21
    ILTER
    -0.21
    DMETHOD
    -0.20
    èĬ¨
    -0.20
    /respond
    -0.20
    uspend
    -0.19
    ajÄħcy
    -0.19
    GINE
    -0.19
    -reply
    -0.19
    POSITIVE LOGITS
     '%$
    0.21
     Remed
    0.20
    åłĤ
    0.20
    allis
    0.19
    ASM
    0.19
     PackageManager
    0.19
    xico
    0.19
     reg
    0.19
     typingsJapgolly
    0.18
    lij
    0.18
    Activations Density 0.000%

    No Known Activations