© 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. 113438
    Prev
    Next
    INDEX
    Explanations

    comparison words (bigger, biggest)

    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
    aby
    -0.10
     menn
    -0.09
    cci
    -0.09
     Braun
    -0.08
     gonna
    -0.08
    ạn
    -0.08
    cratch
    -0.08
     Colleg
    -0.08
    /Library
    -0.08
    omb
    -0.08
    POSITIVE LOGITS
    ós
    0.10
    ass
    0.10
    g
    0.09
    -going
    0.09
    ger
    0.09
    Âł
    0.09
    ãģ°
    0.09
    ariat
    0.09
    Ìģ
    0.08
    778
    0.08
    Activations Density 1.043%

    No Known Activations