© 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. 7415
    Prev
    Next
    INDEX
    Explanations

    stirring or mixing something

    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
     squeeze
    -0.11
     squeezing
    -0.09
     squeez
    -0.09
     hop
    -0.09
     squeezed
    -0.08
     Shotgun
    -0.08
     bridges
    -0.08
     chew
    -0.08
    dbg
    -0.08
    ping
    -0.08
    POSITIVE LOGITS
     stir
    0.25
     stirring
    0.25
     stirred
    0.23
     Stir
    0.22
     unrest
    0.14
     churn
    0.13
     mixing
    0.12
     pot
    0.12
     agitation
    0.12
     pots
    0.12
    Activations Density 0.023%

    No Known Activations