© 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. 7920
    Prev
    Next
    INDEX
    Explanations

    cultural value, heritage, or significance

    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
    ally
    -0.14
    ality
    -0.12
     blister
    -0.11
    jay
    -0.10
    å¼ı
    -0.10
    dea
    -0.10
    ald
    -0.10
    -breaking
    -0.09
    лад
    -0.09
     irresistible
    -0.09
    POSITIVE LOGITS
     heritage
    0.13
    /language
    0.11
    -cultural
    0.11
     relativ
    0.11
     context
    0.10
    mente
    0.10
     Context
    0.10
    /social
    0.10
    herit
    0.10
     diversity
    0.09
    Activations Density 0.049%

    No Known Activations