© 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. 3171
    Prev
    Next
    INDEX
    Explanations

    coding and technical documents

    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
    微软éĽħé»ij
    -0.26
    ]--;↵
    -0.23
    *>(&
    -0.22
     :";↵
    -0.21
    curacy
    -0.21
    -Pack
    -0.21
    ,");↵
    -0.20
    ->__
    -0.20
    quin
    -0.20
    );">↵
    -0.20
    POSITIVE LOGITS
     Hills
    0.21
    åijĬè¯īæĪij们
    0.21
    ordova
    0.21
     inform
    0.20
    edly
    0.20
    åijĬè¯ī
    0.19
    å¾Ī好
    0.18
    èµ°ä¸ĭåİ»
    0.18
    åijĬè¯īæĪij
    0.18
    æĺ¯æľĢ好çļĦ
    0.18
    Activations Density 0.001%

    No Known Activations