© 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. 92625
    Prev
    Next
    INDEX
    Explanations

    enchanting and magical words

    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
    -0.09
     heavier
    -0.09
     vigil
    -0.09
     exploitation
    -0.09
     grat
    -0.09
    aub
    -0.08
     Zig
    -0.08
    agus
    -0.08
     Foley
    -0.08
     satisfaction
    -0.08
    POSITIVE LOGITS
     charm
    0.19
     enchant
    0.17
     charms
    0.16
     captivating
    0.16
     charming
    0.16
     enchanted
    0.16
    charm
    0.15
     magical
    0.13
     myster
    0.13
     Charm
    0.13
    Activations Density 0.001%

    No Known Activations