© 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. 31286
    Prev
    Next
    INDEX
    Explanations

    fireworks or aerial effects

    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
     fran
    -0.10
     hallway
    -0.10
     saddle
    -0.10
     lunches
    -0.09
    ryn
    -0.09
    Shadow
    -0.09
     Lem
    -0.09
     STATS
    -0.09
     substant
    -0.09
    .Pl
    -0.09
    POSITIVE LOGITS
     fireworks
    0.44
     rockets
    0.22
     sparks
    0.19
     Rockets
    0.17
     firing
    0.16
     spark
    0.16
     rocket
    0.16
    /fire
    0.16
     py
    0.16
     ignited
    0.15
    Activations Density 0.147%

    No Known Activations