© 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. 88482
    Prev
    Next
    INDEX
    Explanations

    not

    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
     insured
    -0.10
     wisely
    -0.09
     sufficiently
    -0.09
    ascal
    -0.09
     sufficient
    -0.09
     adequately
    -0.09
     enough
    -0.09
     correctly
    -0.09
     Vig
    -0.08
     properly
    -0.08
    POSITIVE LOGITS
     underestimated
    0.18
     underestimate
    0.17
     overlook
    0.15
     relied
    0.15
     ever
    0.14
     underrated
    0.14
     trusted
    0.13
     EVER
    0.13
     confused
    0.13
     rely
    0.13
    Activations Density 0.056%

    No Known Activations