© 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. 30410
    Prev
    Next
    INDEX
    Explanations

    "you" followed by "should" or "don"

    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
     Rus
    -0.09
     quietly
    -0.09
     christ
    -0.08
     insult
    -0.08
    thanks
    -0.08
     whenever
    -0.08
    pent
    -0.08
    Reuse
    -0.08
     anytime
    -0.08
     dispro
    -0.08
    POSITIVE LOGITS
     warned
    0.24
     warning
    0.22
     warnings
    0.21
     warns
    0.21
     Warning
    0.21
     warn
    0.19
     WARNING
    0.19
    Warning
    0.18
    warning
    0.18
     willingness
    0.17
    Activations Density 0.084%

    No Known Activations