© 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. 4327
    Prev
    Next
    INDEX
    Explanations

    minor issues, easily fixed

    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
     Murphy
    -0.09
     Huntington
    -0.09
    erte
    -0.08
     formally
    -0.08
     yak
    -0.08
    linger
    -0.08
    -fe
    -0.08
    zych
    -0.08
    493
    -0.08
     intricate
    -0.08
    POSITIVE LOGITS
     easily
    0.38
     Easily
    0.33
     manageable
    0.31
     easy
    0.28
    easy
    0.24
     Easy
    0.22
     minor
    0.22
    Easy
    0.21
     removable
    0.21
     negligible
    0.19
    Activations Density 0.264%

    No Known Activations