© 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. 27435
    Prev
    Next
    INDEX
    Explanations

    progression thereafter

    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
    iri
    -0.09
    irst
    -0.09
    .prepend
    -0.09
     Buch
    -0.09
     deadliest
    -0.09
    Tomorrow
    -0.09
     Mint
    -0.08
    ithe
    -0.08
     Enrollment
    -0.08
     newest
    -0.08
    POSITIVE LOGITS
     thereafter
    0.47
     subsequent
    0.43
     subsequently
    0.42
     afterwards
    0.41
     afterward
    0.38
     later
    0.31
     Afterwards
    0.29
     ongoing
    0.27
     continued
    0.27
     once
    0.27
    Activations Density 1.077%

    No Known Activations