© 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. 50955
    Prev
    Next
    INDEX
    Explanations

    conjunctions and reason clauses

    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
     when
    -0.09
     (@
    -0.09
    ools
    -0.09
     redundancy
    -0.09
    when
    -0.09
    /s
    -0.09
     from
    -0.09
    opoly
    -0.09
     perhaps
    -0.09
    -and
    -0.09
    POSITIVE LOGITS
     they
    0.11
    onne
    0.10
    该
    0.09
     Majority
    0.09
     it
    0.09
     полÑĮзоваÑĤ
    0.09
    agen
    0.08
    oord
    0.08
    oger
    0.08
     majority
    0.08
    Activations Density 0.006%

    No Known Activations