© 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. 27620
    Prev
    Next
    INDEX
    Explanations

    pronouns and 'Soviets'

    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
    essler
    -0.09
    (s
    -0.09
    empo
    -0.07
     vacc
    -0.07
     DESC
    -0.07
    -f
    -0.07
    urn
    -0.07
     des
    -0.07
     spanking
    -0.07
    nell
    -0.07
    POSITIVE LOGITS
     Urs
    0.11
     Eis
    0.11
    's
    0.11
     Cla
    0.11
    \'
    0.11
    mar
    0.10
     internally
    0.10
    ’s
    0.10
    ìĿĺ
    0.10
    chest
    0.10
    Activations Density 0.034%

    No Known Activations