© 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. 2759
    Prev
    Next
    INDEX
    Explanations

    Risk Factors

    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
    çĤĿ
    -0.24
     manh
    -0.22
    reements
    -0.21
    ENARIO
    -0.20
    carousel
    -0.20
    iegel
    -0.20
    [strlen
    -0.20
    .TextAlign
    -0.19
    ãģ¾ãģĹãģ¦
    -0.19
    emens
    -0.19
    POSITIVE LOGITS
     Erot
    0.23
     Fetish
    0.23
     ?>↵↵↵
    0.22
     Marketable
    0.22
     Liberties
    0.21
     Wrest
    0.21
    )((((
    0.21
    æŁ¥çľĭåħ¨æĸĩ
    0.21
     recru
    0.21
     scarc
    0.21
    Activations Density 0.001%

    No Known Activations