© 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. 114552
    Prev
    Next
    INDEX
    Explanations

    delay or disruption causes negative effects

    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
     lingering
    -0.11
     healthier
    -0.10
     pimp
    -0.10
     (/
    -0.10
    amt
    -0.10
     sadly
    -0.10
    ullah
    -0.10
     someday
    -0.10
     Produ
    -0.09
     regs
    -0.09
    POSITIVE LOGITS
     delay
    0.18
     delays
    0.17
     jeopard
    0.17
     disruption
    0.16
     disrupted
    0.16
     delaying
    0.15
     disrupting
    0.15
     Delay
    0.15
     disrupt
    0.15
    Delay
    0.15
    Activations Density 0.248%

    No Known Activations