© 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. 27010
    Prev
    Next
    INDEX
    Explanations

    burning and destruction

    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
    Brandon
    -0.10
     abbreviated
    -0.09
     dign
    -0.09
     intense
    -0.08
     intens
    -0.08
     heated
    -0.08
    Shopping
    -0.08
    ignon
    -0.08
     glac
    -0.08
     ign
    -0.08
    POSITIVE LOGITS
     bridges
    0.17
     houses
    0.14
     Bridges
    0.13
     destroyed
    0.13
     buildings
    0.13
     Houses
    0.13
     Buildings
    0.12
     destruction
    0.12
     destroy
    0.12
     bridge
    0.12
    Activations Density 0.035%

    No Known Activations