© 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. 17589
    Prev
    Next
    INDEX
    Explanations

    gold

    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
     Carbon
    -0.13
     slate
    -0.12
     frags
    -0.11
     gray
    -0.11
    -gray
    -0.11
    arbonate
    -0.11
     Grey
    -0.11
     carbonate
    -0.10
     grey
    -0.10
    Carbon
    -0.10
    POSITIVE LOGITS
     gold
    0.66
     golden
    0.56
     Gold
    0.55
     GOLD
    0.55
    gold
    0.54
    Gold
    0.53
    .gold
    0.49
     Golden
    0.48
    _gold
    0.47
    golden
    0.45
    Activations Density 0.523%

    No Known Activations