© 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. 46999
    Prev
    Next
    INDEX
    Explanations

    names starting with capitalized letters

    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
    odore
    -0.12
    etro
    -0.08
    UDO
    -0.08
    oday
    -0.08
     âŁ
    -0.08
    ULO
    -0.08
    ono
    -0.08
    teenth
    -0.08
    sit
    -0.08
     confessed
    -0.08
    POSITIVE LOGITS
    \↵
    0.13
     \↵
    0.11
     inf
    0.11
    ↵
    0.10
    č↵↵
    0.10
    otte
    0.10
    strand
    0.10
    isle
    0.10
    (↵↵
    0.09
    ;;↵↵
    0.09
    Activations Density 0.042%

    No Known Activations