© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113505
    Prev
    Next
    INDEX
    Explanations

    illustrations, demonstrations, product usage

    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
     departed
    -0.11
    oba
    -0.11
    mine
    -0.10
     depart
    -0.10
     Biz
    -0.10
    favorites
    -0.10
    stub
    -0.10
    emade
    -0.10
     sein
    -0.10
     hog
    -0.09
    POSITIVE LOGITS
     product
    0.18
     silhouette
    0.13
    product
    0.12
     illustrations
    0.12
     illustration
    0.12
     usage
    0.11
    /product
    0.11
     PRODUCT
    0.11
     demonstrations
    0.11
     Product
    0.11
    Activations Density 0.041%

    No Known Activations