© 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. 90778
    Prev
    Next
    INDEX
    Explanations

    fiction books and series

    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
     Buddha
    -0.09
     Rutgers
    -0.08
    -Regular
    -0.08
     plaque
    -0.08
     dearly
    -0.08
     homeless
    -0.08
     camer
    -0.08
     Skate
    -0.08
     mú
    -0.08
     Circular
    -0.08
    POSITIVE LOGITS
     novels
    0.18
     novel
    0.17
     book
    0.17
     trilogy
    0.17
     romance
    0.16
     fictional
    0.15
    -book
    0.15
     sequ
    0.14
    /book
    0.14
     books
    0.14
    Activations Density 0.043%

    No Known Activations