© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 89780
    Prev
    Next
    INDEX
    Explanations

    writing Cisco documents, managing, poetry, resolve domains, inaccessible element

    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
    avy
    -0.11
    erra
    -0.11
    ingen
    -0.10
     achie
    -0.09
    jem
    -0.09
     Zac
    -0.09
    ads
    -0.09
    ener
    -0.09
     Survivor
    -0.09
     reco
    -0.09
    POSITIVE LOGITS
    .Execution
    0.10
     hint
    0.09
     intim
    0.09
     disproportion
    0.08
     gateway
    0.08
     clubhouse
    0.08
    oya
    0.08
     implicitly
    0.08
     intimacy
    0.08
     Spend
    0.08
    Activations Density 0.001%

    No Known Activations