© 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. 27491
    Prev
    Next
    INDEX
    Explanations

    phrases indicating source or location

    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
     soccer
    -0.19
     football
    -0.16
     FIFA
    -0.15
     Soccer
    -0.14
    Football
    -0.13
     Football
    -0.13
    football
    -0.13
    -football
    -0.12
     Cowboy
    -0.11
     Shoot
    -0.11
    POSITIVE LOGITS
     robe
    0.27
     robes
    0.22
     monks
    0.18
     gown
    0.17
     monk
    0.15
     Meditation
    0.15
     monastery
    0.14
     meditation
    0.14
     Roku
    0.14
     Spa
    0.13
    Activations Density 0.072%

    No Known Activations