© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 3962
    Prev
    Next
    INDEX
    Explanations

    matrix operations

    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
    gran
    -0.13
     polyline
    -0.10
    lei
    -0.10
    pires
    -0.09
    line
    -0.09
     Fuse
    -0.09
     Pier
    -0.09
    Ķ
    -0.08
     Curve
    -0.08
    enthal
    -0.08
    POSITIVE LOGITS
     matrix
    0.20
     matrices
    0.18
     Matrix
    0.16
     transpose
    0.15
    matrix
    0.15
    Matrix
    0.13
    (matrix
    0.12
    _matrix
    0.12
     Mat
    0.12
     invert
    0.12
    Activations Density 0.173%

    No Known Activations