© 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. 18005
    Prev
    Next
    INDEX
    Explanations

    first something then

    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
     Performing
    -0.11
     performed
    -0.09
     wast
    -0.09
     Newly
    -0.09
     perform
    -0.09
     performs
    -0.09
     newly
    -0.09
     Perform
    -0.09
     anarchist
    -0.09
     craving
    -0.08
    POSITIVE LOGITS
     trips
    0.13
     interviews
    0.12
     surgery
    0.12
     selfies
    0.11
     extremes
    0.11
     baths
    0.11
     vigorous
    0.11
     another
    0.10
     immediate
    0.10
     lectures
    0.10
    Activations Density 0.171%

    No Known Activations