© 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. 27311
    Prev
    Next
    INDEX
    Explanations

    summary or recommendation

    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
    onda
    -0.08
     third
    -0.08
    Regards
    -0.07
     Essays
    -0.07
     foregoing
    -0.07
    rouch
    -0.07
    .Please
    -0.07
     Tran
    -0.07
    !,↵
    -0.07
    isc
    -0.06
    POSITIVE LOGITS
     Explanation
    0.20
     tip
    0.20
     verdict
    0.20
     Tip
    0.20
     Pros
    0.19
     Outcome
    0.19
     explanation
    0.19
    Explanation
    0.18
     Description
    0.18
     Recommendation
    0.18
    Activations Density 0.389%

    No Known Activations