© 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. 89968
    Prev
    Next
    INDEX
    Explanations

    academic articles

    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
     gaz
    -0.09
     Silent
    -0.09
    ifu
    -0.08
     bq
    -0.07
    .sa
    -0.07
    aira
    -0.07
    atch
    -0.07
    airy
    -0.07
    eated
    -0.07
     Crit
    -0.07
    POSITIVE LOGITS
    lien
    0.11
     Toledo
    0.11
     fol
    0.11
     Wer
    0.11
     ServiceProvider
    0.11
     surf
    0.11
    brief
    0.10
     nx
    0.10
     Orleans
    0.10
    (NO
    0.10
    Activations Density 0.001%

    No Known Activations