© 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. 4293
    Prev
    Next
    INDEX
    Explanations

    technology and religious content

    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
    ivol
    -0.23
     erotica
    -0.22
    licted
    -0.22
    缯
    -0.21
    aised
    -0.20
    acerb
    -0.20
     MediaTek
    -0.19
    ÑĢÑĥж
    -0.19
    -notes
    -0.18
    ivos
    -0.18
    POSITIVE LOGITS
    \OptionsResolver
    0.21
    诣
    0.20
    chema
    0.20
    :boolean
    0.19
     Bey
    0.18
    bit
    0.18
     WCHAR
    0.18
    avel
    0.18
     CORPOR
    0.18
    è´¢åĬĽ
    0.18
    Activations Density 0.001%

    No Known Activations