© 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. 45968
    Prev
    Next
    INDEX
    Explanations

    lowering costs or values

    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
     contro
    -0.10
    elas
    -0.09
    estival
    -0.09
    oby
    -0.09
     thrown
    -0.09
    asso
    -0.09
    oro
    -0.09
     Austral
    -0.09
    erti
    -0.09
    oss
    -0.09
    POSITIVE LOGITS
     onto
    0.17
     down
    0.15
     into
    0.14
     lowered
    0.14
     Lower
    0.12
     lowering
    0.12
    into
    0.12
     lower
    0.11
     lowers
    0.11
     below
    0.10
    Activations Density 0.014%

    No Known Activations