© 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. 8525
    Prev
    Next
    INDEX
    Explanations

    results or study

    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
     lle
    -0.12
    erno
    -0.11
    taire
    -0.11
    kees
    -0.10
     hy
    -0.10
     ogl
    -0.10
    ras
    -0.10
    ault
    -0.10
     Carly
    -0.10
    oment
    -0.10
    POSITIVE LOGITS
     accordingly
    0.17
     accompl
    0.11
     certainly
    0.10
     therefore
    0.10
     sure
    0.09
     accomplish
    0.09
     Therefore
    0.08
     attest
    0.08
     exactly
    0.08
     proves
    0.08
    Activations Density 0.760%

    No Known Activations