© 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. 26931
    Prev
    Next
    INDEX
    Explanations

    about context

    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
     decidedly
    -0.10
     absolutely
    -0.09
    aria
    -0.09
     purely
    -0.08
     transit
    -0.08
    urma
    -0.08
     Mos
    -0.08
     tip
    -0.08
     kim
    -0.08
     Presented
    -0.08
    POSITIVE LOGITS
     needing
    0.31
     wanting
    0.25
     being
    0.20
     having
    0.16
     preferring
    0.16
    being
    0.15
     requiring
    0.14
     respecting
    0.13
     expecting
    0.13
     how
    0.13
    Activations Density 0.054%

    No Known Activations