© 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. 28732
    Prev
    Next
    INDEX
    Explanations

    last or latter

    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
    anan
    -0.12
    andan
    -0.11
    ames
    -0.11
    eden
    -0.10
    ?):
    -0.10
    riet
    -0.10
     Merrill
    -0.09
    amat
    -0.09
    emet
    -0.09
     Cooper
    -0.09
    POSITIVE LOGITS
     latter
    0.73
     last
    0.42
    last
    0.31
     Latter
    0.30
    Last
    0.26
     Last
    0.26
    	last
    0.26
    -last
    0.25
     LAST
    0.25
    (last
    0.25
    Activations Density 0.414%

    No Known Activations