© 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. 26206
    Prev
    Next
    INDEX
    Explanations

    mythological figures and roles

    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
     gimm
    -0.10
     nig
    -0.10
     ALWAYS
    -0.10
     incess
    -0.10
     enthusi
    -0.10
     eta
    -0.10
    "is
    -0.09
     itinerary
    -0.09
     Cole
    -0.09
    anye
    -0.09
    POSITIVE LOGITS
     unearth
    0.13
     descended
    0.12
     myth
    0.11
    -like
    0.11
     god
    0.11
     appar
    0.11
     angel
    0.11
    hell
    0.11
     incarn
    0.10
     descend
    0.10
    Activations Density 0.009%

    No Known Activations