© 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. 18679
    Prev
    Next
    INDEX
    Explanations

    information on offerings

    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
     interests
    -0.08
     preced
    -0.08
     xxxx
    -0.08
     Haw
    -0.08
     mentally
    -0.08
    .dds
    -0.08
    "@
    -0.08
     immediate
    -0.08
    amed
    -0.08
    .INSTANCE
    -0.08
    POSITIVE LOGITS
     offers
    0.15
     has
    0.14
     provides
    0.13
     FAQs
    0.12
     allows
    0.12
     is
    0.12
     offer
    0.12
    also
    0.12
     also
    0.12
     boasts
    0.12
    Activations Density 0.018%

    No Known Activations