© 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-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 56197
    Prev
    Next
    INDEX
    Explanations

    sun protection and exposure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lubric
    -0.10
     fluid
    -0.09
    .fm
    -0.09
    Hall
    -0.09
    -fluid
    -0.08
     emptied
    -0.08
     Stability
    -0.08
     discharge
    -0.08
     dac
    -0.08
    ware
    -0.08
    POSITIVE LOGITS
     sun
    0.20
     sunlight
    0.18
     solar
    0.17
     sunscreen
    0.16
    sun
    0.16
     Sun
    0.15
     sung
    0.15
     exposure
    0.14
     sunshine
    0.14
     phot
    0.14
    Activations Density 0.102%

    No Known Activations