© 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. 15379
    Prev
    Next
    INDEX
    Explanations

    origin of this software

    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
     dam
    -0.10
    aby
    -0.10
     organ
    -0.09
    cot
    -0.09
     fur
    -0.09
     Bass
    -0.09
    dam
    -0.08
     Taj
    -0.08
     withhold
    -0.08
     aer
    -0.08
    POSITIVE LOGITS
    judge
    0.10
     surrendered
    0.10
     dile
    0.10
     Rodney
    0.09
    aggregate
    0.09
    nam
    0.09
    nist
    0.09
    enor
    0.09
    GEST
    0.09
    Nam
    0.09
    Activations Density 0.006%

    No Known Activations