© 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. 50271
    Prev
    Next
    INDEX
    Explanations

    expert services

    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
    wand
    -0.09
     online
    -0.08
     Loc
    -0.08
    igt
    -0.08
     posting
    -0.08
     recurring
    -0.08
     grassroots
    -0.08
     everywhere
    -0.08
     orbit
    -0.08
     Wort
    -0.07
    POSITIVE LOGITS
     expertise
    0.17
     specializes
    0.17
     specialists
    0.16
     specialist
    0.16
     specialize
    0.16
    expert
    0.15
     specialised
    0.14
     specialty
    0.14
     clients
    0.14
    Expert
    0.14
    Activations Density 0.047%

    No Known Activations