© 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. 5108
    Prev
    Next
    INDEX
    Explanations

    paid for services or access

    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
    ero
    -0.11
    gie
    -0.09
     jugg
    -0.09
    affer
    -0.08
    nee
    -0.08
     pleasant
    -0.08
     dej
    -0.08
     present
    -0.08
    neo
    -0.08
     bul
    -0.08
    POSITIVE LOGITS
    -for
    0.13
    ups
    0.10
    -up
    0.10
     McKenzie
    0.10
    ewan
    0.10
    igital
    0.10
    arl
    0.09
     lunches
    0.09
    ya
    0.09
    iversity
    0.09
    Activations Density 0.014%

    No Known Activations