© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 111937
    Prev
    Next
    INDEX
    Explanations

    Greek roots and prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dame
    -0.08
    uls
    -0.07
    ver
    -0.06
    cken
    -0.06
    shire
    -0.06
     estate
    -0.06
    itional
    -0.06
    imir
    -0.06
    ieri
    -0.06
    mented
    -0.06
    POSITIVE LOGITS
     Greek
    0.27
    Greek
    0.23
     Greece
    0.21
     Greeks
    0.21
     Athens
    0.19
    erosis
    0.18
     logos
    0.18
    athy
    0.16
    zeug
    0.15
    bios
    0.15
    Activations Density 0.622%

    No Known Activations