© 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. 26820
    Prev
    Next
    INDEX
    Explanations

    web editors

    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
     immediately
    -0.18
     Immediately
    -0.17
     immediate
    -0.16
    Immediately
    -0.15
     Immediate
    -0.13
    Immediate
    -0.12
     INST
    -0.12
     BEFORE
    -0.11
     post
    -0.10
     instantly
    -0.10
    POSITIVE LOGITS
     eventually
    0.38
     Eventually
    0.38
    Eventually
    0.37
     suddenly
    0.28
     Suddenly
    0.27
     eventual
    0.26
     periodically
    0.26
     gradually
    0.25
     occasionally
    0.25
    Suddenly
    0.24
    Activations Density 0.031%

    No Known Activations