© 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. 2706
    Prev
    Next
    INDEX
    Explanations

    technical setup or jargon

    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
    [section
    -0.26
    *l
    -0.23
    cai
    -0.22
    caffold
    -0.22
    .nano
    -0.21
    ','');↵
    -0.21
    ignum
    -0.21
    %c
    -0.20
    zcze
    -0.20
    angs
    -0.20
    POSITIVE LOGITS
    缸éĢļ
    0.23
     órgão
    0.21
    /stretch
    0.20
     vej
    0.20
     fucks
    0.19
    家éĥ½çŁ¥éģĵ
    0.19
    äºı
    0.19
     filmy
    0.19
     ê²ģëĭĪëĭ¤
    0.18
    /facebook
    0.18
    Activations Density 0.002%

    No Known Activations