© 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. 50750
    Prev
    Next
    INDEX
    Explanations

    likely involves or includes

    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
     usually
    -0.16
    usually
    -0.13
     typically
    -0.12
     ordinarily
    -0.11
    Usually
    -0.11
     often
    -0.11
     Usually
    -0.10
     usu
    -0.10
     generally
    -0.09
     normally
    -0.09
    POSITIVE LOGITS
     times
    0.12
    -times
    0.12
     posible
    0.12
     Berk
    0.12
     misunder
    0.12
    times
    0.11
     colle
    0.11
     POSS
    0.11
     TIMES
    0.11
    ogue
    0.11
    Activations Density 0.014%

    No Known Activations