© 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. 5131
    Prev
    Next
    INDEX
    Explanations

    book writing and publishing

    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
     Official
    -0.09
     repetition
    -0.09
     Sawyer
    -0.09
    ilm
    -0.09
     replication
    -0.09
     enchanted
    -0.08
     Marl
    -0.08
     finely
    -0.08
     ers
    -0.08
     continuation
    -0.08
    POSITIVE LOGITS
     manuscript
    0.18
     manuscripts
    0.17
     drafts
    0.17
     underway
    0.15
     draft
    0.15
     ready
    0.15
     unpublished
    0.15
     Manus
    0.14
     internally
    0.14
     drafted
    0.13
    Activations Density 0.428%

    No Known Activations