© 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. 3453
    Prev
    Next
    INDEX
    Explanations

    be verbs

    np_max-act-logits · gemini-2.5-flash-lite
    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
    \admin
    -0.21
    aed
    -0.21
     ê²½ìļ°ìĹIJëĬĶ
    -0.20
    ://${
    -0.19
     Vuex
    -0.19
     Während
    -0.19
    efd
    -0.19
    (strtolower
    -0.18
    éĢ¡
    -0.18
    )throws
    -0.18
    POSITIVE LOGITS
    naments
    0.24
     utan
    0.23
     sik
    0.21
    IconButton
    0.20
     damer
    0.20
    égor
    0.20
    udiant
    0.20
    Got
    0.19
    ymous
    0.19
    }}">{{$
    0.19
    Activations Density 0.261%

    No Known Activations