© 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. 6633
    Prev
    Next
    INDEX
    Explanations

    size and UK sizing

    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
    Strip
    -0.12
     strip
    -0.12
     strips
    -0.11
    strip
    -0.11
     Barnes
    -0.11
    flags
    -0.11
     stripped
    -0.10
     NFC
    -0.10
     punct
    -0.10
     Strip
    -0.10
    POSITIVE LOGITS
     sizes
    0.39
     sizing
    0.38
     size
    0.36
     Size
    0.32
     sized
    0.32
     Sizes
    0.32
    sizes
    0.30
    -size
    0.29
    size
    0.29
    Size
    0.28
    Activations Density 0.226%

    No Known Activations