© 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. 2651
    Prev
    Next
    INDEX
    Explanations

    numbers and sequences

    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
    以åıĬ
    -0.20
    lav
    -0.20
     Sche
    -0.20
    æļ¨
    -0.19
    zyst
    -0.19
    acks
    -0.19
    ami
    -0.19
    رØŃÙħ
    -0.18
     **************************************************************************
    -0.18
    filme
    -0.18
    POSITIVE LOGITS
     bénéficie
    0.24
     Xiaomi
    0.23
    uguay
    0.22
     addCriterion
    0.20
    åĩ¡æľ¬ç½ij
    0.20
     dequeueReusableCellWithIdentifier
    0.20
    ".↵↵↵↵
    0.20
     PROFITS
    0.20
     createState
    0.20
    OpenHelper
    0.20
    Activations Density 0.158%

    No Known Activations