© 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. 92499
    Prev
    Next
    INDEX
    Explanations

    school holidays and closures

    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
    yar
    -0.09
    077
    -0.09
     class
    -0.08
     Sav
    -0.08
     squat
    -0.08
     Engines
    -0.08
    -vars
    -0.08
     letz
    -0.08
    ritz
    -0.08
     epit
    -0.08
    POSITIVE LOGITS
    arra
    0.10
    icode
    0.10
    wil
    0.09
    acon
    0.09
     $#
    0.09
     cynical
    0.09
     Eh
    0.09
     alo
    0.09
     Schwar
    0.09
     sus
    0.09
    Activations Density 0.003%

    No Known Activations