© 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. 47204
    Prev
    Next
    INDEX
    Explanations

    emerging field or category

    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
    adies
    -0.11
    acio
    -0.09
    uzu
    -0.09
    inaire
    -0.09
     Structure
    -0.09
     poem
    -0.09
    fab
    -0.09
     sched
    -0.09
    headline
    -0.09
     Kurt
    -0.08
    POSITIVE LOGITS
     genre
    0.41
     category
    0.31
     phenomenon
    0.28
     niche
    0.28
     Genre
    0.27
    genre
    0.27
     genres
    0.25
     branch
    0.25
     trend
    0.24
     sector
    0.23
    Activations Density 0.472%

    No Known Activations