© 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. 33097
    Prev
    Next
    INDEX
    Explanations

    delay or slowness

    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
     Intr
    -0.10
     adults
    -0.10
     increasingly
    -0.10
     tomorrow
    -0.09
     immediately
    -0.09
     adult
    -0.09
     nightly
    -0.09
     regimes
    -0.09
     Abr
    -0.09
     daily
    -0.08
    POSITIVE LOGITS
     delayed
    0.21
     Delay
    0.21
     delays
    0.20
     delay
    0.20
    -delay
    0.19
     delaying
    0.19
    delay
    0.18
     slower
    0.18
    Delay
    0.18
     lag
    0.18
    Activations Density 0.092%

    No Known Activations