© 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. 31793
    Prev
    Next
    INDEX
    Explanations

    whole or entire noun

    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
     frankly
    -0.09
     Gee
    -0.09
     scoff
    -0.09
    933
    -0.08
     gee
    -0.08
    ISP
    -0.08
    zin
    -0.08
    GAN
    -0.08
    ars
    -0.08
     hin
    -0.08
    POSITIVE LOGITS
     autogenerated
    0.10
    788
    0.09
     Nacht
    0.09
     collapses
    0.09
    atra
    0.09
     empt
    0.09
     society
    0.09
     person
    0.09
    eid
    0.09
     Eggs
    0.09
    Activations Density 0.006%

    No Known Activations