© 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. 25018
    Prev
    Next
    INDEX
    Explanations

    what is

    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
     inconvenience
    -0.10
     differently
    -0.09
     is
    -0.09
     needing
    -0.09
     anonymously
    -0.08
    alles
    -0.08
    atz
    -0.08
    LOY
    -0.08
    Being
    -0.08
     belonging
    -0.08
    POSITIVE LOGITS
     supposed
    0.32
     gonna
    0.24
     meant
    0.18
     worth
    0.18
     suppose
    0.17
     called
    0.17
     going
    0.16
     able
    0.15
     comprised
    0.15
     afraid
    0.15
    Activations Density 0.112%

    No Known Activations