© 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. 89160
    Prev
    Next
    INDEX
    Explanations

    conjunctions or prepositions after punctuation

    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
    —which
    -0.11
    anel
    -0.11
    agens
    -0.10
    herits
    -0.09
    plural
    -0.09
    /format
    -0.09
     Urb
    -0.09
    bidden
    -0.09
    yles
    -0.09
     Earn
    -0.09
    POSITIVE LOGITS
    ered
    0.09
     Oro
    0.09
    .rd
    0.09
    .if
    0.08
     mime
    0.08
     mf
    0.08
    lap
    0.08
    elles
    0.08
     UNS
    0.07
     jap
    0.07
    Activations Density 0.273%

    No Known Activations