© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 30160
    Prev
    Next
    INDEX
    Explanations

    incarnation and rebirth

    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
     Ced
    -0.11
     NAN
    -0.10
     Fres
    -0.10
     Derrick
    -0.10
     erect
    -0.10
     adjustable
    -0.10
     vacancy
    -0.10
     upkeep
    -0.10
     acknowledgment
    -0.09
    cb
    -0.09
    POSITIVE LOGITS
     reinc
    0.56
     incarn
    0.36
     incarnation
    0.36
     reb
    0.33
     birth
    0.20
     born
    0.18
     Birth
    0.18
     respawn
    0.18
    arnation
    0.17
     births
    0.17
    Activations Density 0.075%

    No Known Activations