© 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. 48530
    Prev
    Next
    INDEX
    Explanations

    technology, autos, services, marketing, university

    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
     locality
    -0.10
     Clarkson
    -0.10
    /as
    -0.09
     Stard
    -0.09
    :\"
    -0.09
    rikes
    -0.09
    lrt
    -0.09
    oman
    -0.09
    odo
    -0.09
     diss
    -0.09
    POSITIVE LOGITS
     Floyd
    0.09
     advancements
    0.08
     scape
    0.08
     SHARES
    0.08
     Angels
    0.08
     disconnect
    0.08
     roaring
    0.08
    ipur
    0.08
    .vn
    0.08
     Stack
    0.08
    Activations Density 0.443%

    No Known Activations