© 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. 5883
    Prev
    Next
    INDEX
    Explanations

    names with non-Latin characters

    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
    atum
    -0.08
    FIN
    -0.08
     overwhelm
    -0.08
    bourg
    -0.08
     Mold
    -0.08
    ushima
    -0.08
    ulg
    -0.08
    efs
    -0.07
     deter
    -0.07
     overwhelmingly
    -0.07
    POSITIVE LOGITS
     fo
    0.10
     dele
    0.10
    ove
    0.09
    rico
    0.09
     Cement
    0.09
     pig
    0.09
    .sym
    0.09
    gram
    0.09
     complimentary
    0.09
     rib
    0.09
    Activations Density 0.003%

    No Known Activations