© 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. 14862
    Prev
    Next
    INDEX
    Explanations

    description and studies

    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
    .Match
    -0.12
     Amir
    -0.10
     Directorate
    -0.10
     institution
    -0.10
     CENT
    -0.10
     logo
    -0.10
     enclave
    -0.10
     amph
    -0.09
     logos
    -0.09
     brass
    -0.09
    POSITIVE LOGITS
    /misc
    0.10
     Dew
    0.09
     shelves
    0.09
     Misc
    0.08
     voc
    0.08
    Misc
    0.08
     call
    0.08
     handicap
    0.08
     divorce
    0.08
    æij
    0.08
    Activations Density 0.222%

    No Known Activations