© 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. 31314
    Prev
    Next
    INDEX
    Explanations

    upon + action/event

    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
     Trem
    -0.09
    iap
    -0.08
    gie
    -0.07
    vel
    -0.07
     Bien
    -0.07
    ött
    -0.07
     phenomenon
    -0.07
     Apost
    -0.07
    toggle
    -0.07
     cont
    -0.07
    POSITIVE LOGITS
     arrival
    0.18
     completion
    0.18
     receipt
    0.16
     entering
    0.15
     realizing
    0.15
     arriving
    0.14
     closer
    0.14
     completing
    0.14
    completion
    0.14
     seeing
    0.14
    Activations Density 0.042%

    No Known Activations