© 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. 26880
    Prev
    Next
    INDEX
    Explanations

    encompass

    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
     Crud
    -0.11
    ship
    -0.11
     Engel
    -0.10
     McCart
    -0.10
     constitution
    -0.10
     cautiously
    -0.10
    /live
    -0.10
    constitution
    -0.10
     foll
    -0.09
    linger
    -0.09
    POSITIVE LOGITS
     encompass
    0.11
     sum
    0.09
    ports
    0.09
     contained
    0.09
    ed
    0.08
     incorporated
    0.08
    erer
    0.08
    brands
    0.08
     encaps
    0.08
    rips
    0.08
    Activations Density 0.006%

    No Known Activations