© 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. 1512
    Prev
    Next
    INDEX
    Explanations

    word suffixes

    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
    linky
    -0.44
    ojis
    -0.40
    bable
    -0.40
    chedulers
    -0.39
    tsy
    -0.37
    gings
    -0.36
    chestra
    -0.36
    phia
    -0.36
    semb
    -0.36
    ections
    -0.36
    POSITIVE LOGITS
    ly
    0.54
    ous
    0.47
    ie
    0.44
    ian
    0.43
    ic
    0.43
    ary
    0.43
    æĢ§çļĦ
    0.42
    st
    0.41
    al
    0.41
    age
    0.40
    Activations Density 8.307%

    No Known Activations