© 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. 48666
    Prev
    Next
    INDEX
    Explanations

    logs

    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
    oku
    -0.10
     psych
    -0.09
     border
    -0.08
     sav
    -0.08
     accumulated
    -0.08
     permutations
    -0.08
     hass
    -0.08
     ast
    -0.08
    illard
    -0.08
     armed
    -0.08
    POSITIVE LOGITS
     hive
    0.12
    zo
    0.12
    /providers
    0.12
    inner
    0.11
    nio
    0.11
    eries
    0.11
     Reviewed
    0.11
    OPLE
    0.10
     Rex
    0.10
     bless
    0.10
    Activations Density 0.424%

    No Known Activations