© 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. 27309
    Prev
    Next
    INDEX
    Explanations

    ago

    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
    urer
    -0.10
     Close
    -0.10
     Alphabet
    -0.10
     Amid
    -0.10
    nez
    -0.10
    lov
    -0.10
    heimer
    -0.10
    okens
    -0.09
     congreg
    -0.09
    rogate
    -0.09
    POSITIVE LOGITS
     ago
    0.16
    phia
    0.10
     Ago
    0.10
     DEC
    0.09
     cent
    0.09
     contraction
    0.09
     years
    0.09
     fix
    0.09
     contracted
    0.08
     months
    0.08
    Activations Density 0.015%

    No Known Activations