© 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. 3486
    Prev
    Next
    INDEX
    Explanations

    technical terms and titles

    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
     )}↵↵
    -0.21
    并ä¸įæĺ¯å¾Ī
    -0.21
     }};↵
    -0.21
    çĿ¥
    -0.20
     Viagra
    -0.20
    ãģ¦ãģıãĤĮãģŁ
    -0.20
    parer
    -0.19
    ç»ijæŀ¶
    -0.19
    	↵	↵↵
    -0.18
     Gore
    -0.18
    POSITIVE LOGITS
    .AutoScaleMode
    0.22
     Natürlich
    0.20
    ---</
    0.20
    reactstrap
    0.20
    cona
    0.20
    nav
    0.20
    åİŁæĸĩåľ°åĿĢ
    0.20
    :NO
    0.19
    noch
    0.19
    /os
    0.19
    Activations Density 0.008%

    No Known Activations