© 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. 50870
    Prev
    Next
    INDEX
    Explanations

    biographical details

    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
     decl
    -0.10
    imei
    -0.09
    yar
    -0.08
    udas
    -0.08
    ichte
    -0.08
     positively
    -0.08
     stitches
    -0.08
    /thumb
    -0.08
     final
    -0.08
     FIT
    -0.08
    POSITIVE LOGITS
    Website
    0.17
     Website
    0.16
     Visit
    0.13
     Contact
    0.12
    Contact
    0.12
     contact
    0.12
     bio
    0.12
    bio
    0.12
     website
    0.12
    Visit
    0.12
    Activations Density 0.136%

    No Known Activations