© 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. 31336
    Prev
    Next
    INDEX
    Explanations

    how things are done

    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
    iken
    -0.09
     Winn
    -0.08
    omite
    -0.08
    emb
    -0.08
     Kurd
    -0.08
     Ree
    -0.08
     Castillo
    -0.07
    kid
    -0.07
     Schneider
    -0.07
    itar
    -0.07
    POSITIVE LOGITS
     handled
    0.30
     behave
    0.29
     behaved
    0.28
     behaves
    0.27
     handling
    0.26
     approached
    0.23
     handle
    0.22
     Handling
    0.22
     handles
    0.22
     interact
    0.22
    Activations Density 0.492%

    No Known Activations