© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 13955
    Prev
    Next
    INDEX
    Explanations

    free shipping

    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
    Negative Logits
     da
    -0.10
    adan
    -0.09
     cost
    -0.09
    ax
    -0.09
    oda
    -0.08
    Verb
    -0.08
    zel
    -0.08
     remodel
    -0.08
     sod
    -0.08
     ab
    -0.08
    POSITIVE LOGITS
     bilateral
    0.11
     thereafter
    0.11
     impacted
    0.09
     Burgess
    0.09
    cola
    0.09
     Rash
    0.09
     Rex
    0.09
     onstage
    0.09
     Pavel
    0.09
     menace
    0.09
    Activations Density 0.083%

    No Known Activations