© 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. 2845
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    ,DB
    -0.25
    rvine
    -0.23
    xfff
    -0.22
    ï¼ģ",
    -0.21
    <![
    -0.20
     }//
    -0.19
    åĴĮ社ä¼ļ
    -0.19
    楼ä¸ĭ
    -0.19
     esac
    -0.19
    byss
    -0.19
    POSITIVE LOGITS
    ĵĺ
    0.22
    .MouseAdapter
    0.21
    mour
    0.20
    .ActionListener
    0.20
    æģIJ
    0.20
    entar
    0.20
    ifestyles
    0.20
    تÙĥÙĪÙĨ
    0.19
     ConfigureServices
    0.19
    paralleled
    0.19
    Activations Density 0.003%

    No Known Activations