© 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. 397
    Prev
    Next
    INDEX
    Explanations

    word endings

    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
     minY
    -0.23
    acists
    -0.23
    cuador
    -0.23
    haled
    -0.23
    sembles
    -0.22
     dumpsters
    -0.22
    strstr
    -0.22
    voie
    -0.20
    	fflush
    -0.20
    .fhir
    -0.20
    POSITIVE LOGITS
    etheless
    0.55
    adays
    0.52
    xiety
    0.45
    gether
    0.43
    ematics
    0.39
    ematic
    0.37
    tempts
    0.35
    ellaneous
    0.34
    ÑįÑĤомÑĥ
    0.32
    onacci
    0.32
    Activations Density 4.758%

    No Known Activations