© 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. 32778
    Prev
    Next
    INDEX
    Explanations

    measures and statistics

    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
     mutually
    -0.10
     Lori
    -0.10
    emed
    -0.09
     demands
    -0.09
    ofi
    -0.09
    cow
    -0.09
     inher
    -0.09
    ogi
    -0.09
     Zus
    -0.09
    ayne
    -0.09
    POSITIVE LOGITS
     ranged
    0.22
     exceeds
    0.21
     equals
    0.20
     exceeded
    0.18
     varies
    0.18
     exceed
    0.17
     amounted
    0.17
     excluding
    0.16
     ranges
    0.15
     rose
    0.15
    Activations Density 1.263%

    No Known Activations