© 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. 17573
    Prev
    Next
    INDEX
    Explanations

    Shakespeare's works and stage productions

    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
     BEL
    -0.09
     Planned
    -0.09
     interesting
    -0.08
    kus
    -0.08
     Marcos
    -0.08
     planned
    -0.08
     adj
    -0.08
     Midnight
    -0.08
     stimulating
    -0.08
    ON
    -0.08
    POSITIVE LOGITS
     pun
    0.10
     pretty
    0.10
     lurking
    0.09
    sic
    0.09
    ctl
    0.09
     explosive
    0.09
    nit
    0.09
     Pretty
    0.09
    Downloads
    0.09
     anyone
    0.09
    Activations Density 0.007%

    No Known Activations