© 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. 28706
    Prev
    Next
    INDEX
    Explanations

    actions or processes followed by conjunctions

    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
     exclus
    -0.09
    ffen
    -0.09
    nger
    -0.09
     eben
    -0.09
    (es
    -0.08
    UMMY
    -0.08
     proceeding
    -0.08
    uala
    -0.08
     aussi
    -0.08
    åıĬ
    -0.08
    POSITIVE LOGITS
     vign
    0.10
     Vincent
    0.10
     chunk
    0.10
     Fir
    0.10
    chunk
    0.09
    exion
    0.09
    isser
    0.09
     distr
    0.09
     miniature
    0.09
     vacc
    0.09
    Activations Density 0.012%

    No Known Activations