© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2177
    Prev
    Next
    INDEX
    Explanations

    countries

    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
    对åħ¶çľŁå®ŀ
    -0.27
    ulings
    -0.26
    )(((
    -0.26
    âĹĤ
    -0.24
    ibraltar
    -0.24
    )((((
    -0.24
    iare
    -0.23
    -LAST
    -0.23
    DRV
    -0.23
     Relatives
    -0.23
    POSITIVE LOGITS
    0.23
    2
    0.22
     trick
    0.20
     pylab
    0.20
    /
    0.20
    车éĹ´
    0.19
     page
    0.19
    5
    0.19
    3
    0.19
    ,
    0.19
    Activations Density 0.389%

    No Known Activations