© 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. 46248
    Prev
    Next
    INDEX
    Explanations

    email addresses and mailto links

    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
    Not in Any Lists

    No Comments

    Negative Logits
    :@
    -0.11
    -record
    -0.11
     laps
    -0.10
     opport
    -0.10
    lav
    -0.10
     misd
    -0.10
     Govern
    -0.10
    azaar
    -0.10
    rs
    -0.10
     opp
    -0.10
    POSITIVE LOGITS
     titles
    0.08
     contents
    0.08
     Nich
    0.08
    loh
    0.08
    illage
    0.07
     novels
    0.07
    اد
    0.07
     найд
    0.07
    /google
    0.07
    frey
    0.07
    Activations Density 0.001%

    No Known Activations