© 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. 15352
    Prev
    Next
    INDEX
    Explanations

    binary and conditional 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
    DEM
    -0.10
    ypse
    -0.08
    Sharper
    -0.08
    ksam
    -0.08
    iar
    -0.08
     transl
    -0.08
    “At
    -0.08
    iba
    -0.08
     Localization
    -0.08
    779
    -0.08
    POSITIVE LOGITS
     Petro
    0.10
    udo
    0.09
     daddy
    0.09
    contre
    0.09
     absolutely
    0.09
     Bik
    0.09
     dozens
    0.08
     (↵
    0.08
    lis
    0.08
    rib
    0.08
    Activations Density 0.552%

    No Known Activations