© 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. 114681
    Prev
    Next
    INDEX
    Explanations

    afterwards, thereafter, subsequently

    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
    bett
    -0.10
    igner
    -0.09
    /Images
    -0.09
    AZE
    -0.09
    Nam
    -0.09
     Died
    -0.09
     Crime
    -0.09
     beh
    -0.09
    iets
    -0.09
     whole
    -0.08
    POSITIVE LOGITS
     afterwards
    0.11
     afterward
    0.11
     OPTION
    0.10
     specifically
    0.10
     therein
    0.10
     thereafter
    0.10
     meanwhile
    0.09
    åħ¶ä¸Ń
    0.09
     consequently
    0.09
     Nights
    0.09
    Activations Density 1.898%

    No Known Activations