© 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. 34008
    Prev
    Next
    INDEX
    Explanations

    enough or sufficiently

    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
     Coll
    -0.10
     Lex
    -0.10
     chop
    -0.10
    chy
    -0.10
     persists
    -0.09
    REA
    -0.09
     Chad
    -0.09
     Arnold
    -0.09
    omi
    -0.09
     McCain
    -0.09
    POSITIVE LOGITS
     enough
    0.16
     Enough
    0.11
    Enough
    0.11
    AndGet
    0.11
     sufficiently
    0.10
     better
    0.10
     emotionally
    0.10
     intellectually
    0.10
     deeply
    0.10
    itere
    0.10
    Activations Density 0.261%

    No Known Activations