© 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. 115622
    Prev
    Next
    INDEX
    Explanations

    names ending in 'a' or 'an'

    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
     rpt
    -0.08
     Beetle
    -0.08
    incident
    -0.08
    elim
    -0.07
    Latch
    -0.07
    netinet
    -0.07
     Jade
    -0.07
     dough
    -0.07
     emblem
    -0.07
    /packages
    -0.07
    POSITIVE LOGITS
    iento
    0.10
    /loading
    0.10
     WAN
    0.09
     clap
    0.09
     yan
    0.09
    annie
    0.09
     ansible
    0.09
    IFn
    0.09
    .randrange
    0.09
     Leisure
    0.09
    Activations Density 3.279%

    No Known Activations