© 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. 3411
    Prev
    Next
    INDEX
    Explanations

    soap operas and serials

    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
     perch
    -0.11
     Netflix
    -0.11
     rut
    -0.11
    Netflix
    -0.10
    VICE
    -0.10
     Beard
    -0.10
     Observatory
    -0.10
     Elon
    -0.10
     HBO
    -0.10
     YA
    -0.10
    POSITIVE LOGITS
     soap
    0.21
     Soap
    0.19
     SOAP
    0.16
    Soap
    0.15
    soap
    0.15
     storyline
    0.15
    SOAP
    0.14
     Opera
    0.12
     daytime
    0.11
     schem
    0.11
    Activations Density 0.352%

    No Known Activations