© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 89902
    Prev
    Next
    INDEX
    Explanations

    physical dimensions and measurements

    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
     Tight
    -0.10
     tight
    -0.10
     tighter
    -0.10
    tight
    -0.10
     positional
    -0.09
    omi
    -0.09
     bump
    -0.09
    ansson
    -0.09
    jr
    -0.09
    amen
    -0.08
    POSITIVE LOGITS
     approximately
    0.22
     size
    0.22
     roughly
    0.21
     diameter
    0.20
     length
    0.20
     dimensions
    0.20
     sized
    0.20
     Size
    0.19
     Length
    0.19
     Approximately
    0.19
    Activations Density 0.287%

    No Known Activations