© 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. 89706
    Prev
    Next
    INDEX
    Explanations

    meanwhile

    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
     presumably
    -0.10
     boss
    -0.10
     surrogate
    -0.10
     partner
    -0.09
     revealing
    -0.09
     Boss
    -0.09
     est
    -0.09
     ord
    -0.09
    partner
    -0.09
     appropriate
    -0.08
    POSITIVE LOGITS
     meanwhile
    0.29
    Meanwhile
    0.28
     Meanwhile
    0.28
     meantime
    0.21
     unaware
    0.19
     unknow
    0.17
     unwitting
    0.16
     elsewhere
    0.15
     unsus
    0.15
     upstairs
    0.15
    Activations Density 0.021%

    No Known Activations