© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 137
    Prev
    Next
    INDEX
    Explanations

    that" "ryanair" "children" "permit" "combined"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whenever
    -0.10
     ways
    -0.10
     wherever
    -0.10
     whereas
    -0.10
     dah
    -0.09
    ãĢĤ
    -0.09
    .
    -0.09
    :
    -0.09
     because
    -0.09
     ðŁĺī↵↵
    -0.09
    POSITIVE LOGITS
    "is
    0.15
    ients
    0.11
    ANNOT
    0.11
    verts
    0.10
    )did
    0.10
    .SO
    0.10
    ?]
    0.10
    —is
    0.10
     _)
    0.09
    —are
    0.09
    Activations Density 3.935%

    No Known Activations