© 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. 113336
    Prev
    Next
    INDEX
    Explanations

    setting fire, pages removed, taking apart

    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
     recal
    -0.10
     mint
    -0.09
     Adjust
    -0.09
     âĢİ
    -0.08
    rides
    -0.08
    Adjust
    -0.08
     adjusting
    -0.08
     Perc
    -0.08
     Kut
    -0.08
    841
    -0.08
    POSITIVE LOGITS
     faster
    0.14
     Faster
    0.13
     fastest
    0.13
     pile
    0.13
     discarded
    0.12
     quicker
    0.12
     piled
    0.12
     piles
    0.11
     quickest
    0.11
    èIJ
    0.11
    Activations Density 0.016%

    No Known Activations