© 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. 7427
    Prev
    Next
    INDEX
    Explanations

    boring, bored, or dull

    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
     fierc
    -0.12
     startled
    -0.11
     frantic
    -0.11
    arella
    -0.10
     fier
    -0.10
     panicked
    -0.10
     unsett
    -0.10
     fren
    -0.10
     panic
    -0.09
    ç®±
    -0.09
    POSITIVE LOGITS
     boring
    0.62
     boredom
    0.54
     bored
    0.54
     dull
    0.42
     tedious
    0.41
     bore
    0.39
     monot
    0.28
     unins
    0.27
     bland
    0.27
     enn
    0.26
    Activations Density 0.224%

    No Known Activations