© 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. 16956
    Prev
    Next
    INDEX
    Explanations

    literary content 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
     footage
    -0.17
     DVD
    -0.14
     video
    -0.13
     Video
    -0.13
     vide
    -0.13
     Television
    -0.12
    TV
    -0.12
     cameras
    -0.12
     music
    -0.11
     videos
    -0.11
    POSITIVE LOGITS
     literary
    0.21
     Literary
    0.18
     writers
    0.18
     novels
    0.17
     reading
    0.16
     Writers
    0.16
     prose
    0.15
     reads
    0.15
    writers
    0.15
     erotica
    0.14
    Activations Density 0.013%

    No Known Activations