© 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. 115550
    Prev
    Next
    INDEX
    Explanations

    skin color and flushing

    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
     refr
    -0.09
     romant
    -0.08
    riba
    -0.08
     Sizes
    -0.08
     pepp
    -0.08
    ouden
    -0.08
     erot
    -0.08
    otton
    -0.07
     Lub
    -0.07
     laz
    -0.07
    POSITIVE LOGITS
     pale
    0.34
     color
    0.24
     Pale
    0.24
     pall
    0.24
     flushed
    0.23
     complexion
    0.23
    Pale
    0.21
     flushing
    0.21
     redd
    0.20
     colour
    0.20
    Activations Density 0.066%

    No Known Activations