© 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. 50893
    Prev
    Next
    INDEX
    Explanations

    names like Kim, Phillips, Williams, Samsung

    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
     Newfoundland
    -0.12
     Malta
    -0.11
     Dante
    -0.10
     Sloven
    -0.09
     Slovenia
    -0.09
     Jasper
    -0.09
     Cyprus
    -0.09
     Haj
    -0.09
     Estonia
    -0.09
     kne
    -0.09
    POSITIVE LOGITS
     Kim
    0.19
    Kim
    0.18
     Kimberly
    0.18
     Pyongyang
    0.17
     kim
    0.17
     Seoul
    0.16
     Samsung
    0.15
     Kimber
    0.15
     Koreans
    0.14
    Samsung
    0.14
    Activations Density 0.160%

    No Known Activations