© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4242
    Prev
    Next
    INDEX
    Explanations

    code or data

    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
    Negative Logits
    emean
    -0.24
    ábado
    -0.23
    yk
    -0.22
     bä
    -0.21
     Decompiled
    -0.21
    curities
    -0.21
    /Branch
    -0.20
    exter
    -0.20
    :numel
    -0.20
    ornment
    -0.20
    POSITIVE LOGITS
    åħļé£İ
    0.22
    åĬŀæ³ķ
    0.21
    åıĪ好åıĪå¿«
    0.21
     ula
    0.19
    æĶ¾åĩº
    0.19
    LOUR
    0.18
    çĿ¹
    0.18
    æĢ»ä¼ļ
    0.18
    xFE
    0.18
     Ann
    0.18
    Activations Density 0.005%

    No Known Activations