© 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. 90593
    Prev
    Next
    INDEX
    Explanations

    sun protection and heat risks

    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
     rain
    -0.13
     Halloween
    -0.11
    jal
    -0.11
     Christmas
    -0.11
     Valentine
    -0.10
     Gur
    -0.10
    rain
    -0.10
     pimp
    -0.10
    Christmas
    -0.10
     fet
    -0.10
    POSITIVE LOGITS
     sunscreen
    0.13
     towel
    0.10
     umbrella
    0.10
     sunt
    0.10
     SPF
    0.10
     blot
    0.10
     volleyball
    0.09
     Binder
    0.09
     intolerance
    0.09
     shaded
    0.09
    Activations Density 0.054%

    No Known Activations