© 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. 31341
    Prev
    Next
    INDEX
    Explanations

    state of being after "was" or "were"

    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
     dw
    -0.10
     reck
    -0.09
    ALT
    -0.09
     clam
    -0.08
     Sms
    -0.08
     disob
    -0.08
     voluntarily
    -0.08
    042
    -0.08
     enthusiastically
    -0.08
     reacting
    -0.08
    POSITIVE LOGITS
     nett
    0.13
     perplex
    0.13
     tempted
    0.12
     stunned
    0.12
     shocked
    0.12
     startled
    0.12
     intrig
    0.11
     mort
    0.11
     app
    0.11
     baff
    0.11
    Activations Density 0.028%

    No Known Activations