© 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. 27430
    Prev
    Next
    INDEX
    Explanations

    came, received, arrived, delivery

    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
    iro
    -0.09
    /pages
    -0.08
     scrape
    -0.08
     inverted
    -0.08
     enact
    -0.08
    logout
    -0.08
     elig
    -0.08
     scram
    -0.08
    Pag
    -0.08
     Carlson
    -0.08
    POSITIVE LOGITS
     arrive
    0.35
     arrived
    0.34
     arrives
    0.34
     arrival
    0.32
     arriving
    0.32
     arrivals
    0.29
     Arrival
    0.26
     arriv
    0.25
     delivered
    0.24
     delivery
    0.23
    Activations Density 0.221%

    No Known Activations