© 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. 116332
    Prev
    Next
    INDEX
    Explanations

    groups with multiple options

    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
     afterwards
    -0.08
     afterward
    -0.08
    hoa
    -0.08
     albeit
    -0.07
     next
    -0.07
    anda
    -0.07
     wherever
    -0.07
     Huck
    -0.07
     beyond
    -0.07
     Nobel
    -0.07
    POSITIVE LOGITS
     ordinary
    0.28
     conventional
    0.25
     single
    0.24
     normal
    0.24
     straightforward
    0.24
     alone
    0.23
     outright
    0.23
     singly
    0.23
     solo
    0.22
     Single
    0.22
    Activations Density 3.397%

    No Known Activations