© 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. 3476
    Prev
    Next
    INDEX
    Explanations

    Uni, mini

    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
    ¡´
    -0.38
    -Cs
    -0.34
    ,Yes
    -0.34
     Seks
    -0.33
    #aa
    -0.33
    'icon
    -0.33
     )))
    -0.32
    :';↵
    -0.32
    TÃľ
    -0.31
    inati
    -0.31
    POSITIVE LOGITS
     sofas
    0.31
    0.30
    0
    0.28
    1
    0.28
    -
    0.28
    3
    0.27
    A
    0.27
    S
    0.27
     undefeated
    0.27
    s
    0.26
    Activations Density 3.143%

    No Known Activations