© 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. 114331
    Prev
    Next
    INDEX
    Explanations

    errors and mistakes

    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
     missing
    -0.14
     stolen
    -0.12
     lost
    -0.11
     loss
    -0.11
     impaired
    -0.11
     failure
    -0.10
     disrupted
    -0.10
     unreliable
    -0.10
     destroyed
    -0.10
     Missing
    -0.09
    POSITIVE LOGITS
     incurred
    0.14
     incur
    0.14
     committed
    0.14
     unavoidable
    0.13
     Avoid
    0.13
     tolerated
    0.13
    Avoid
    0.13
     perpetrated
    0.13
     toler
    0.13
    committed
    0.13
    Activations Density 0.281%

    No Known Activations