© 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. 48004
    Prev
    Next
    INDEX
    Explanations

    fire and fury

    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
     shady
    -0.10
    phones
    -0.09
     Shade
    -0.09
     sunglasses
    -0.09
     vibrations
    -0.09
     sweating
    -0.09
     dirt
    -0.09
    rena
    -0.09
    /forum
    -0.09
     Leather
    -0.09
    POSITIVE LOGITS
     ðŁĶ
    0.17
     extingu
    0.16
    .Fire
    0.15
     passion
    0.15
     passions
    0.14
     arson
    0.13
    brands
    0.12
    /fire
    0.12
     ignited
    0.12
     blaze
    0.12
    Activations Density 0.091%

    No Known Activations