© 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. 2906
    Prev
    Next
    INDEX
    Explanations

    technical art

    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
    =admin
    -0.22
    ·»
    -0.21
    .setCancelable
    -0.19
    .requires
    -0.18
    avana
    -0.18
     Zuk
    -0.18
    weeted
    -0.18
    azor
    -0.18
    anean
    -0.18
    utomation
    -0.18
    POSITIVE LOGITS
    PTY
    0.21
    iá»ĩn
    0.21
    oriously
    0.21
    edReader
    0.20
    :"-
    0.20
    alement
    0.20
    >Title
    0.20
     %↵↵
    0.19
    :convert
    0.19
    gnore
    0.19
    Activations Density 0.001%

    No Known Activations