© 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. 16706
    Prev
    Next
    INDEX
    Explanations

    decisions after waiting or before acting

    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
     appropriately
    -0.11
    bw
    -0.09
     surprising
    -0.09
     surprisingly
    -0.08
    acr
    -0.08
    BW
    -0.08
     uncomfort
    -0.08
     disappoint
    -0.08
    lik
    -0.08
    kr
    -0.08
    POSITIVE LOGITS
     impulse
    0.13
     underestimated
    0.13
     agreeing
    0.13
     impuls
    0.13
     agreed
    0.12
     stupid
    0.12
     greedy
    0.12
     insisted
    0.11
     insistence
    0.11
     ambitious
    0.11
    Activations Density 0.032%

    No Known Activations