© 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. 27456
    Prev
    Next
    INDEX
    Explanations

    thunder and lightning

    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
     weather
    -0.14
     sunny
    -0.13
     cé
    -0.12
    weather
    -0.12
     Weather
    -0.11
     swe
    -0.10
     surre
    -0.10
     nons
    -0.10
    sky
    -0.10
    -google
    -0.10
    POSITIVE LOGITS
     lightning
    0.40
     Lightning
    0.33
     thunder
    0.22
     flashes
    0.22
     Thunder
    0.21
     hail
    0.19
    Thunder
    0.17
     lighting
    0.16
     flash
    0.15
     Lighting
    0.14
    Activations Density 0.142%

    No Known Activations