© 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. 92600
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions

    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
     vandal
    -0.12
    ince
    -0.10
    ices
    -0.10
     —↵↵
    -0.10
    amos
    -0.10
     Cork
    -0.10
     subdiv
    -0.10
    argon
    -0.10
     Tavern
    -0.09
     Audit
    -0.09
    POSITIVE LOGITS
    prit
    0.08
    ogi
    0.08
     Fist
    0.08
     advancements
    0.08
     Same
    0.08
    HN
    0.08
     Latter
    0.08
    DEM
    0.07
    HM
    0.07
     Brom
    0.07
    Activations Density 0.001%

    No Known Activations