© 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. 90092
    Prev
    Next
    INDEX
    Explanations

    act Parliament

    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
     expedition
    -0.10
    YM
    -0.10
     problems
    -0.09
    topic
    -0.09
     Topic
    -0.09
     stakes
    -0.09
     lax
    -0.09
     topics
    -0.09
     lessons
    -0.09
     intensive
    -0.09
    POSITIVE LOGITS
     performed
    0.25
     acts
    0.25
     act
    0.20
     Acts
    0.19
    Performed
    0.19
    acts
    0.18
    Acts
    0.18
     perform
    0.17
     performs
    0.16
     Perform
    0.16
    Activations Density 0.038%

    No Known Activations