© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114545
    Prev
    Next
    INDEX
    Explanations

    explaining definitions or terms

    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
     detailed
    -0.10
    -analysis
    -0.10
     Analysis
    -0.10
     analysis
    -0.10
    ouve
    -0.10
     Detailed
    -0.09
    Detailed
    -0.09
     Math
    -0.09
    Analysis
    -0.09
    详
    -0.09
    POSITIVE LOGITS
     definitions
    0.21
     terminology
    0.20
    Definitions
    0.18
     Termin
    0.18
     basics
    0.18
     termin
    0.17
     Definitions
    0.17
    definitions
    0.15
     basic
    0.15
     definition
    0.15
    Activations Density 0.182%

    No Known Activations