© 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. 111887
    Prev
    Next
    INDEX
    Explanations

    when I want to backup or remind

    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
     yearly
    -0.13
     annual
    -0.12
     daily
    -0.12
     Peyton
    -0.10
     Annual
    -0.10
    woke
    -0.10
     christmas
    -0.10
     annually
    -0.09
     Easter
    -0.09
     perpetual
    -0.09
    POSITIVE LOGITS
     recourse
    0.14
     automatically
    0.13
     remembering
    0.13
     immediately
    0.13
     resort
    0.13
     readily
    0.13
     remembered
    0.13
     reminder
    0.12
     remember
    0.12
     reminded
    0.12
    Activations Density 0.244%

    No Known Activations