© 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. 30203
    Prev
    Next
    INDEX
    Explanations

    Commotion and excitement

    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
     lux
    -0.11
     creeping
    -0.09
    undos
    -0.09
    opi
    -0.09
     elusive
    -0.09
     Gibbs
    -0.09
    avez
    -0.09
     liebe
    -0.09
     perch
    -0.09
     tempt
    -0.09
    POSITIVE LOGITS
     fuss
    0.36
     disturbance
    0.26
     comm
    0.26
     controversy
    0.24
     upro
    0.23
     stir
    0.23
     stirred
    0.22
     excitement
    0.22
     hype
    0.21
     disturbances
    0.20
    Activations Density 0.097%

    No Known Activations