© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 18097
    Prev
    Next
    INDEX
    Explanations

    professions and roles

    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
     ect
    -0.12
     evacuated
    -0.10
    cket
    -0.09
     kel
    -0.09
    ACKET
    -0.09
    unnel
    -0.09
    acr
    -0.09
    alis
    -0.09
    icals
    -0.08
     ils
    -0.08
    POSITIVE LOGITS
     disguised
    0.11
     reb
    0.11
     born
    0.10
     wrapped
    0.10
     amongst
    0.10
     Bowman
    0.09
     forever
    0.09
     among
    0.09
     atl
    0.09
     slash
    0.09
    Activations Density 0.092%

    No Known Activations