© 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. 28146
    Prev
    Next
    INDEX
    Explanations

    definitions, technical terms, or specialized vocabulary

    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
    ango
    -0.11
     emotion
    -0.11
     laughter
    -0.10
    Ł³
    -0.10
     verbally
    -0.10
     Gifts
    -0.10
     neg
    -0.10
    perms
    -0.10
     glue
    -0.10
     birthdays
    -0.10
    POSITIVE LOGITS
     rav
    0.09
     Estr
    0.09
     pretext
    0.08
     footh
    0.08
     guise
    0.08
     ausp
    0.08
     Neal
    0.08
     stronghold
    0.08
     rendez
    0.08
     footing
    0.08
    Activations Density 0.709%

    No Known Activations