© 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. 34245
    Prev
    Next
    INDEX
    Explanations

    is an existence indicator

    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
    ï¿
    -0.10
     Kab
    -0.09
    .sw
    -0.09
     Irr
    -0.09
    usc
    -0.08
    ical
    -0.08
     Cath
    -0.08
    igr
    -0.08
     SAS
    -0.08
    umber
    -0.08
    POSITIVE LOGITS
    лем
    0.10
    oland
    0.10
     indeb
    0.09
     Lid
    0.09
    /Peak
    0.09
     Patent
    0.09
    /Dk
    0.09
    -scenes
    0.09
     ae
    0.09
     freaking
    0.09
    Activations Density 0.003%

    No Known Activations