© 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. 15968
    Prev
    Next
    INDEX
    Explanations

    development and application

    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
     quar
    -0.12
    orang
    -0.11
     pretending
    -0.11
     shards
    -0.10
     Assist
    -0.10
    eria
    -0.10
    Engine
    -0.10
    ť
    -0.10
     crunch
    -0.10
    é¢Ŀ
    -0.10
    POSITIVE LOGITS
     China
    0.13
    China
    0.11
     vigorously
    0.11
     Hun
    0.11
     Chinese
    0.10
    éĢīæĭ
    0.10
     contradictions
    0.10
     laying
    0.10
     grop
    0.10
     informat
    0.10
    Activations Density 3.479%

    No Known Activations