© 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. 29662
    Prev
    Next
    INDEX
    Explanations

    throne and podium mentions

    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
    orgot
    -0.10
    pole
    -0.10
    aban
    -0.09
     arist
    -0.09
    lice
    -0.09
    umin
    -0.09
    à¸ļ
    -0.09
    remium
    -0.09
    æ¥
    -0.09
    rist
    -0.09
    POSITIVE LOGITS
     Room
    0.11
     room
    0.11
     vac
    0.10
     Ded
    0.10
     vacant
    0.09
     Meh
    0.09
    vac
    0.09
    bbing
    0.09
     Rape
    0.09
     Vall
    0.09
    Activations Density 0.003%

    No Known Activations