© 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. 89617
    Prev
    Next
    INDEX
    Explanations

    sudden negative events, loss

    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
     refreshed
    -0.09
     reunited
    -0.08
     new
    -0.08
     newfound
    -0.08
     improved
    -0.08
     Impro
    -0.07
     leftovers
    -0.07
     reinc
    -0.07
     newcom
    -0.07
     outsiders
    -0.07
    POSITIVE LOGITS
     normally
    0.19
     Losing
    0.19
     suddenly
    0.18
     relied
    0.18
     loss
    0.17
     abruptly
    0.17
     valued
    0.17
     sudden
    0.17
     cherished
    0.17
     losing
    0.16
    Activations Density 1.049%

    No Known Activations