© 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. 33981
    Prev
    Next
    INDEX
    Explanations

    when it comes time

    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
     Kerr
    -0.09
     hamm
    -0.08
    alia
    -0.08
    Jur
    -0.08
     Bak
    -0.08
     SID
    -0.08
    ({...
    -0.08
     ,"
    -0.08
     Jur
    -0.07
    anel
    -0.07
    POSITIVE LOGITS
     needing
    0.15
     crunch
    0.15
     actual
    0.14
     need
    0.13
    need
    0.12
    Actual
    0.12
     inevitably
    0.11
    Need
    0.11
    actual
    0.11
     time
    0.11
    Activations Density 0.150%

    No Known Activations