© 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. 89537
    Prev
    Next
    INDEX
    Explanations

    dark, shiny, glossy

    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
     costumes
    -0.12
     Tall
    -0.12
    extras
    -0.11
     eup
    -0.11
     boots
    -0.10
    ppy
    -0.10
    aggi
    -0.10
     wheelchair
    -0.10
    ĵį
    -0.10
     costume
    -0.10
    POSITIVE LOGITS
     inviting
    0.15
     darker
    0.15
     visible
    0.15
     pink
    0.13
     darkest
    0.13
     shiny
    0.12
     dark
    0.11
     darken
    0.11
     glossy
    0.11
     translucent
    0.11
    Activations Density 0.023%

    No Known Activations