© 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. 33484
    Prev
    Next
    INDEX
    Explanations

    ord start

    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
     irrespective
    -0.10
     costing
    -0.09
    igma
    -0.09
     regardless
    -0.09
    stash
    -0.09
    alytics
    -0.09
    iegel
    -0.09
     favoured
    -0.09
    inan
    -0.09
    ungan
    -0.09
    POSITIVE LOGITS
     ere
    0.10
     dilig
    0.10
    oler
    0.08
     Bingo
    0.08
     misd
    0.08
    irut
    0.08
    ingen
    0.08
     bears
    0.08
    :max
    0.08
    cer
    0.08
    Activations Density 0.003%

    No Known Activations