© 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. 49360
    Prev
    Next
    INDEX
    Explanations

    size increase

    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
    unner
    -0.11
    Cole
    -0.11
     consort
    -0.10
    FIN
    -0.10
     Woj
    -0.10
    ipa
    -0.10
     clustered
    -0.10
    czy
    -0.10
    zc
    -0.09
     FIN
    -0.09
    POSITIVE LOGITS
     swelling
    0.17
     expansion
    0.17
     size
    0.17
     expanding
    0.17
     swell
    0.16
     expand
    0.16
     enlarge
    0.16
     expands
    0.15
     enlargement
    0.15
     enlarg
    0.15
    Activations Density 0.025%

    No Known Activations