© 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. 115758
    Prev
    Next
    INDEX
    Explanations

    numbers, weights, or sizes

    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
     approximately
    -0.11
     Approximately
    -0.09
     length
    -0.09
     roughly
    -0.09
    Approx
    -0.09
     approx
    -0.08
     saliva
    -0.08
     longest
    -0.08
    midd
    -0.08
    approx
    -0.07
    POSITIVE LOGITS
     rumours
    0.14
     outweigh
    0.12
     weighed
    0.12
    iert
    0.12
     Estimate
    0.11
     Shed
    0.11
     packed
    0.11
    tiles
    0.11
     estimation
    0.10
    zend
    0.10
    Activations Density 0.025%

    No Known Activations