© 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. 90271
    Prev
    Next
    INDEX
    Explanations

    superlatives then yet/ever

    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
    afil
    -0.11
    edi
    -0.10
     dragged
    -0.09
     Barton
    -0.09
     QA
    -0.09
    cal
    -0.09
    687
    -0.09
    QA
    -0.09
     misunderstood
    -0.09
     Harper
    -0.08
    POSITIVE LOGITS
     yet
    0.32
     ever
    0.29
    yet
    0.23
     EVER
    0.22
     Yet
    0.22
    -ever
    0.22
    Yet
    0.21
     bisher
    0.19
    ever
    0.18
     Ever
    0.16
    Activations Density 0.197%

    No Known Activations