© 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. 27288
    Prev
    Next
    INDEX
    Explanations

    giving new definition or meaning

    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
     Bucks
    -0.09
     Wen
    -0.08
    =key
    -0.08
     Thumbnail
    -0.08
     Starter
    -0.08
     Wan
    -0.08
    Ven
    -0.08
    adol
    -0.08
    apos
    -0.08
    bour
    -0.08
    POSITIVE LOGITS
     meaning
    0.56
     Meaning
    0.46
     meanings
    0.45
    meaning
    0.43
     definition
    0.29
    Mean
    0.27
    -mean
    0.26
     Definition
    0.24
    æĦı
    0.23
    definition
    0.22
    Activations Density 0.102%

    No Known Activations