© 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. 18010
    Prev
    Next
    INDEX
    Explanations

    with/after punctuation or common words

    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
     colorful
    -0.10
     Grim
    -0.10
    eln
    -0.08
     av
    -0.08
     ach
    -0.08
     Estates
    -0.08
     brightly
    -0.08
     Crafts
    -0.08
     wis
    -0.07
    -progress
    -0.07
    POSITIVE LOGITS
     ramifications
    0.15
     gilt
    0.12
     quantity
    0.12
     populous
    0.12
     commod
    0.11
     quo
    0.11
     motto
    0.11
    quo
    0.11
    -extra
    0.11
    alternate
    0.11
    Activations Density 0.399%

    No Known Activations