© 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. 89511
    Prev
    Next
    INDEX
    Explanations

    consider, seeks, could, but, probably

    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
     endeavor
    -0.11
     heavenly
    -0.11
     endeavors
    -0.10
     administrations
    -0.10
    Resolve
    -0.10
     Cla
    -0.10
     vigor
    -0.10
     BBQ
    -0.10
     incarnation
    -0.10
     Ere
    -0.10
    POSITIVE LOGITS
     Indian
    0.12
     juga
    0.11
     Dal
    0.11
     sadly
    0.11
     India
    0.10
     dal
    0.10
     Indians
    0.09
     debunk
    0.09
     sust
    0.09
     sensit
    0.09
    Activations Density 0.584%

    No Known Activations