© 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. 26660
    Prev
    Next
    INDEX
    Explanations

    weighing scale measurements

    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
    ouv
    -0.11
     lap
    -0.10
     vel
    -0.10
     Cath
    -0.10
    Vel
    -0.10
     Vel
    -0.10
     laps
    -0.09
     Vere
    -0.09
     Mull
    -0.09
     Booker
    -0.09
    POSITIVE LOGITS
     weighing
    0.50
     weigh
    0.50
     weighed
    0.44
    weigh
    0.43
     weighs
    0.37
     scales
    0.34
     weights
    0.33
     weight
    0.33
     scale
    0.32
     Weight
    0.30
    Activations Density 0.311%

    No Known Activations