© 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. 6750
    Prev
    Next
    INDEX
    Explanations

    Powered by, Sponsored by, Licensed under

    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
     Prest
    -0.10
    enum
    -0.10
    ings
    -0.10
     visits
    -0.09
    fr
    -0.09
    generation
    -0.09
    674
    -0.09
     Nathan
    -0.09
     bucket
    -0.09
     intelligence
    -0.09
    POSITIVE LOGITS
    usercontent
    0.10
     indeb
    0.10
     bye
    0.09
     sweaty
    0.09
    emet
    0.09
     Shar
    0.09
     courte
    0.08
     gul
    0.08
     aval
    0.08
     alm
    0.08
    Activations Density 0.013%

    No Known Activations