© 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. 17269
    Prev
    Next
    INDEX
    Explanations

    dates and months

    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
     sar
    -0.09
     exempt
    -0.09
     numbering
    -0.09
    614
    -0.08
     Spicer
    -0.08
     Hutchinson
    -0.08
     mill
    -0.08
    weg
    -0.08
     aggressive
    -0.08
     Posted
    -0.08
    POSITIVE LOGITS
     theirs
    0.10
     yours
    0.10
    -Origin
    0.10
     minded
    0.10
    eed
    0.10
    feito
    0.09
    ece
    0.09
     tin
    0.09
     Moss
    0.09
     Material
    0.09
    Activations Density 0.002%

    No Known Activations