© 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. 4486
    Prev
    Next
    INDEX
    Explanations

    spicing up dull or stale things

    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
     proudly
    -0.09
    Wer
    -0.09
     sigh
    -0.09
     Ferry
    -0.09
     wishes
    -0.09
     Wer
    -0.08
     wished
    -0.08
     unm
    -0.08
     dripping
    -0.08
    aeda
    -0.08
    POSITIVE LOGITS
     routine
    0.15
     dull
    0.14
     monot
    0.14
     Routine
    0.13
     boring
    0.13
     repertoire
    0.13
     otherwise
    0.13
     lacking
    0.12
     stale
    0.12
     routines
    0.12
    Activations Density 0.025%

    No Known Activations