© 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. 49262
    Prev
    Next
    INDEX
    Explanations

    use data or coupon

    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
     dou
    -0.11
    tings
    -0.10
     weighed
    -0.09
    ssc
    -0.09
     forget
    -0.09
     strapped
    -0.09
     cel
    -0.09
    oru
    -0.09
     Covent
    -0.09
    ìļ
    -0.09
    POSITIVE LOGITS
     implied
    0.09
    akah
    0.09
    zee
    0.09
     strengths
    0.09
     neon
    0.08
    Thread
    0.08
    /interface
    0.08
    -www
    0.07
     Morrison
    0.07
    zig
    0.07
    Activations Density 0.001%

    No Known Activations