© 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. 48949
    Prev
    Next
    INDEX
    Explanations

    numbers and scientific/medical terms

    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
    jab
    -0.09
     Mand
    -0.08
     Mitchell
    -0.08
    atu
    -0.08
    ensi
    -0.08
     reco
    -0.08
     âŁ
    -0.08
     Bias
    -0.08
     Emb
    -0.08
     esl
    -0.08
    POSITIVE LOGITS
     psyche
    0.11
     sober
    0.11
     fray
    0.11
    -Mart
    0.10
     carn
    0.10
     incontro
    0.10
     Addiction
    0.10
     acknow
    0.10
    %d
    0.09
    empre
    0.09
    Activations Density 0.008%

    No Known Activations