© 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. 114384
    Prev
    Next
    INDEX
    Explanations

    cancel, change, postpone

    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
     Dorm
    -0.11
     Grad
    -0.10
     gradually
    -0.10
    timestamps
    -0.10
     gradual
    -0.10
     gib
    -0.10
    Displayed
    -0.09
     Transitional
    -0.09
     alien
    -0.09
    grad
    -0.09
    POSITIVE LOGITS
     unexpected
    0.35
     cancellation
    0.34
     unexpectedly
    0.33
     cancelled
    0.33
     cancell
    0.32
     unfore
    0.32
     canceled
    0.31
     cancel
    0.30
     postpon
    0.29
     Cancel
    0.29
    Activations Density 0.493%

    No Known Activations