© 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. 15627
    Prev
    Next
    INDEX
    Explanations

    synthetic material blends

    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
     wooden
    -0.11
     Wooden
    -0.09
     requisite
    -0.09
     Tin
    -0.09
     jq
    -0.09
     external
    -0.08
     majestic
    -0.08
     LOD
    -0.08
     sal
    -0.08
     tonic
    -0.08
    POSITIVE LOGITS
     proprietary
    0.15
     derivatives
    0.14
     blends
    0.14
     cousin
    0.13
     synthetic
    0.13
     Synthetic
    0.13
     derivative
    0.12
     variants
    0.12
     hybrids
    0.11
     blended
    0.11
    Activations Density 0.340%

    No Known Activations