© 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. 112846
    Prev
    Next
    INDEX
    Explanations

    wrong or incorrect

    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
     looming
    -0.10
    vang
    -0.09
     Noticed
    -0.09
    .utc
    -0.09
     blat
    -0.08
    ulti
    -0.08
    uber
    -0.08
    Sad
    -0.08
    ihar
    -0.08
    itar
    -0.08
    POSITIVE LOGITS
     wrong
    0.54
     incorrect
    0.50
     incorrectly
    0.50
     wrongly
    0.46
     Wrong
    0.42
    wrong
    0.41
     improperly
    0.41
     Incorrect
    0.40
     inappropriate
    0.39
    Wrong
    0.37
    Activations Density 1.326%

    No Known Activations