© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 30308
    Prev
    Next
    INDEX
    Explanations

    sun and light exposure

    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
     sunlight
    -0.32
     sunshine
    -0.30
     sun
    -0.30
     Sun
    -0.28
     sunny
    -0.27
    sun
    -0.26
    Sun
    -0.25
     Sunshine
    -0.25
    _sun
    -0.24
     SUN
    -0.23
    POSITIVE LOGITS
    .mozilla
    0.09
    ibern
    0.09
     impro
    0.08
    beck
    0.08
     mood
    0.08
    orde
    0.08
     Disco
    0.08
    ubar
    0.08
    ages
    0.08
    orio
    0.08
    Activations Density 0.162%

    No Known Activations