© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48260
    Prev
    Next
    INDEX
    Explanations

    technical articles and electronic components

    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
     biome
    -0.11
     MPI
    -0.10
     dpi
    -0.10
    steel
    -0.10
     mpi
    -0.10
     TAR
    -0.10
     steel
    -0.09
     OPS
    -0.09
     discs
    -0.09
     Bentley
    -0.09
    POSITIVE LOGITS
     solder
    0.31
     circuit
    0.29
     resistor
    0.28
     transistor
    0.28
     PCB
    0.28
     Circuit
    0.27
     Arduino
    0.26
     circuits
    0.25
     voltage
    0.24
    Arduino
    0.23
    Activations Density 5.462%

    No Known Activations