© 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. 4369
    Prev
    Next
    INDEX
    Explanations

    sunlight and light effects

    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
     blunt
    -0.11
     Burr
    -0.10
     duplic
    -0.09
     Turnbull
    -0.09
     Zw
    -0.09
    jn
    -0.09
     Blur
    -0.09
     Grip
    -0.09
     Radar
    -0.09
    oes
    -0.09
    POSITIVE LOGITS
     sunlight
    0.31
     beams
    0.27
     beam
    0.25
     rays
    0.24
     sunshine
    0.23
    beam
    0.23
     shaft
    0.22
    Beam
    0.19
     Beam
    0.19
     ray
    0.18
    Activations Density 0.115%

    No Known Activations