© 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. 116446
    Prev
    Next
    INDEX
    Explanations

    of a generation / of status / of war / of reason

    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
    -archive
    -0.09
     nail
    -0.09
     Nail
    -0.08
     Sting
    -0.08
    ungs
    -0.08
     Corpor
    -0.07
     rendez
    -0.07
    .experimental
    -0.07
    ilton
    -0.07
     Hayward
    -0.07
    POSITIVE LOGITS
     sorts
    0.14
     circumstance
    0.12
    ump
    0.12
     capitalism
    0.11
     society
    0.11
    SORT
    0.10
    /form
    0.10
     nature
    0.10
    /pre
    0.10
    ordion
    0.10
    Activations Density 0.108%

    No Known Activations