© 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. 3069
    Prev
    Next
    INDEX
    Explanations

    version numbers

    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
    au
    -0.23
    åħ¬
    -0.19
    .optString
    -0.19
     åķ
    -0.19
    lias
    -0.19
    icz
    -0.18
     erg
    -0.18
    zym
    -0.18
    yssey
    -0.18
    ste
    -0.18
    POSITIVE LOGITS
     onPause
    0.26
    ABCDEFGHIJKLMNOP
    0.21
    datable
    0.21
    /avatar
    0.20
    轫
    0.20
    Winvalid
    0.20
    =\"#
    0.20
    ($('<
    0.20
    <quote
    0.20
    ÙħÙĪÙĤع
    0.20
    Activations Density 0.354%

    No Known Activations