© 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. 15059
    Prev
    Next
    INDEX
    Explanations

    units of measurement (per volume/weight/time)

    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
    imately
    -0.11
     weekly
    -0.09
    ered
    -0.09
     shel
    -0.09
     quest
    -0.09
     Weekly
    -0.08
    Weekly
    -0.08
    asha
    -0.08
    imat
    -0.08
     stiff
    -0.08
    POSITIVE LOGITS
     hour
    0.21
     litre
    0.17
     per
    0.16
     HOUR
    0.16
     minute
    0.15
    hour
    0.15
    Hour
    0.15
    /sec
    0.15
     Hour
    0.15
     gallon
    0.14
    Activations Density 0.216%

    No Known Activations