© 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. 3292
    Prev
    Next
    INDEX
    Explanations

    technical or administrative context

    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
    egasus
    -0.23
    andelier
    -0.21
    GetPosition
    -0.20
    .sponge
    -0.20
    #echo
    -0.20
     washington
    -0.19
    reib
    -0.19
    æľĭåıĭ们对
    -0.19
    disposing
    -0.19
     NOTHING
    -0.19
    POSITIVE LOGITS
    æĤĶ
    0.25
    oundingBox
    0.24
    åĨ°æ·ĩ
    0.23
    -ves
    0.22
    cação
    0.22
    uales
    0.20
    rapped
    0.20
    ¡´
    0.20
    ,ev
    0.20
    bove
    0.20
    Activations Density 0.001%

    No Known Activations