© 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. 54723
    Prev
    Next
    INDEX
    Explanations

    rationalization and rationality

    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
    roz
    -0.09
    onical
    -0.09
    uously
    -0.08
    ounce
    -0.08
    obel
    -0.08
    WISE
    -0.08
     Horton
    -0.08
    jes
    -0.08
    ied
    -0.08
    CLA
    -0.08
    POSITIVE LOGITS
    ity
    0.23
    er
    0.10
    alf
    0.10
    ally
    0.10
    ating
    0.10
    enburg
    0.10
    ITY
    0.10
     Unified
    0.10
    imon
    0.10
    bins
    0.09
    Activations Density 0.003%

    No Known Activations