© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5620
    Prev
    Next
    INDEX
    Explanations

    actor names

    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
     Fairfield
    -0.09
    --,
    -0.09
     Nimbus
    -0.09
     Conversation
    -0.09
     Georgetown
    -0.08
    (Level
    -0.08
     CSC
    -0.08
     CCT
    -0.08
     RFC
    -0.08
    CHIP
    -0.08
    POSITIVE LOGITS
     actress
    0.21
     actor
    0.20
     Actress
    0.19
     actors
    0.19
     actresses
    0.19
     celebrity
    0.16
     Actors
    0.16
     Actor
    0.16
    /model
    0.16
     celebrities
    0.16
    Activations Density 0.238%

    No Known Activations