© 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. 4177
    Prev
    Next
    INDEX
    Explanations

    numbers, durations, or amounts

    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
    moth
    -0.10
     Bail
    -0.10
    ritt
    -0.09
    anka
    -0.09
     Twist
    -0.09
     bail
    -0.09
     refere
    -0.09
    -render
    -0.09
    .yy
    -0.09
    -parse
    -0.09
    POSITIVE LOGITS
    /from
    0.15
     Conversely
    0.14
    /un
    0.13
    /not
    0.13
     either
    0.12
    /to
    0.12
    /-
    0.12
    /de
    0.11
    either
    0.11
     +/-
    0.11
    Activations Density 0.727%

    No Known Activations