© 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. 26574
    Prev
    Next
    INDEX
    Explanations

    quantities and numbers

    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
     Too
    -0.11
     EVEN
    -0.10
     too
    -0.09
     worse
    -0.09
     Feng
    -0.09
     truly
    -0.09
     even
    -0.09
    Too
    -0.09
    owie
    -0.08
     proves
    -0.08
    POSITIVE LOGITS
     hundreds
    0.23
     dozens
    0.22
     thousands
    0.21
     incess
    0.19
     nearly
    0.18
     millions
    0.18
     gigantic
    0.18
     forty
    0.17
     fifty
    0.17
     seventy
    0.17
    Activations Density 0.360%

    No Known Activations