© 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. 7784
    Prev
    Next
    INDEX
    Explanations

    happening or finished events

    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
     eventual
    -0.09
     eventually
    -0.09
     vari
    -0.09
     Eventually
    -0.09
    prox
    -0.08
    Eventually
    -0.08
     disput
    -0.08
     antis
    -0.08
     exist
    -0.08
     Hayes
    -0.08
    POSITIVE LOGITS
     officially
    0.14
     crystall
    0.14
     suddenly
    0.13
     proven
    0.13
     validated
    0.13
     unfolding
    0.13
     proved
    0.12
     confirmed
    0.12
     abruptly
    0.12
    este
    0.12
    Activations Density 0.119%

    No Known Activations