© 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. 28192
    Prev
    Next
    INDEX
    Explanations

    aesthetic beauty and design

    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
    erness
    -0.13
     Wien
    -0.11
    erved
    -0.11
     lab
    -0.11
     пов
    -0.10
    CHASE
    -0.10
     prod
    -0.10
    quiv
    -0.10
    ’es
    -0.10
    bove
    -0.10
    POSITIVE LOGITS
     pleasing
    0.08
     underwater
    0.08
     bed
    0.08
    aar
    0.08
     humid
    0.07
     Worcester
    0.07
    antas
    0.07
    Ideal
    0.07
    ideo
    0.07
     ideal
    0.07
    Activations Density 0.002%

    No Known Activations