© 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. 3391
    Prev
    Next
    INDEX
    Explanations

    this includes

    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
    aras
    -0.08
    anova
    -0.08
     commanded
    -0.08
    acd
    -0.08
     Monad
    -0.07
     Monter
    -0.07
     marital
    -0.07
    LT
    -0.07
    contest
    -0.07
     Marino
    -0.07
    POSITIVE LOGITS
     clip
    0.11
     ones
    0.10
    686
    0.10
    arel
    0.10
     unn
    0.10
    sein
    0.10
     dint
    0.10
     Thurs
    0.10
    imos
    0.10
     Phonetic
    0.10
    Activations Density 0.004%

    No Known Activations