© 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. 91376
    Prev
    Next
    INDEX
    Explanations

    agreement/disagreement and correctness

    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
     refl
    -0.11
    udu
    -0.11
     unpl
    -0.10
     pau
    -0.10
    odos
    -0.10
     Edu
    -0.09
    (encoding
    -0.09
     rq
    -0.09
    oir
    -0.09
     fet
    -0.09
    POSITIVE LOGITS
     disagree
    0.13
     wrong
    0.13
     regarding
    0.13
     disagreement
    0.12
     about
    0.12
     Regarding
    0.12
     disagreed
    0.12
     correctness
    0.11
     dispute
    0.11
    wrong
    0.10
    Activations Density 0.147%

    No Known Activations