© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 25186
    Prev
    Next
    INDEX
    Explanations

    short fiction and poems

    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
    Negative Logits
     Chapters
    -0.17
     chapters
    -0.14
     Chapter
    -0.14
     chapter
    -0.14
     CHAPTER
    -0.12
    Chapter
    -0.11
     senate
    -0.11
    CHAPTER
    -0.11
     Personality
    -0.10
    chapter
    -0.10
    POSITIVE LOGITS
     short
    0.20
     fiction
    0.17
     Short
    0.16
     poems
    0.16
     shorts
    0.16
     poem
    0.15
    Short
    0.15
     anthology
    0.15
    short
    0.15
     Fiction
    0.14
    Activations Density 0.629%

    No Known Activations