© 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. 25021
    Prev
    Next
    INDEX
    Explanations

    after or soon

    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
    aret
    -0.10
     Volk
    -0.09
    unes
    -0.09
     affirm
    -0.08
    ire
    -0.08
     unn
    -0.08
     Exp
    -0.08
    lex
    -0.08
    753
    -0.08
     acceler
    -0.08
    POSITIVE LOGITS
     once
    0.19
     AFTER
    0.19
    once
    0.19
     momentarily
    0.17
    soon
    0.15
     soon
    0.14
     Once
    0.14
     after
    0.14
    after
    0.14
    Once
    0.14
    Activations Density 0.132%

    No Known Activations