© 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. 4323
    Prev
    Next
    INDEX
    Explanations

    case citations

    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
    :'.$
    -0.25
    __;
    -0.25
    èij¶
    -0.21
     Fireplace
    -0.21
     Packs
    -0.21
    fono
    -0.21
    ).^
    -0.21
    storybook
    -0.21
     Cald
    -0.21
    strtotime
    -0.21
    POSITIVE LOGITS
     last
    0.21
     startActivityForResult
    0.20
    æľĢåIJİä¸Ģ个
    0.19
    è¶ħé«ĺ
    0.18
     finally
    0.18
     GetComponent
    0.18
    ky
    0.18
     end
    0.18
    æ¾Ħ
    0.18
     ep
    0.18
    Activations Density 0.160%

    No Known Activations