© 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. 90147
    Prev
    Next
    INDEX
    Explanations

    mild or slight reduction

    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
     absolutely
    -0.25
     incredibly
    -0.24
     utterly
    -0.22
     incredible
    -0.22
     enormously
    -0.22
     tremendously
    -0.22
     masterpiece
    -0.21
     endlessly
    -0.21
     forever
    -0.21
     EVERY
    -0.21
    POSITIVE LOGITS
     mildly
    0.22
     slightly
    0.22
     somewhat
    0.21
     occasionally
    0.20
     occasional
    0.20
     briefly
    0.18
     slight
    0.18
     partially
    0.17
     lightly
    0.17
     temporarily
    0.16
    Activations Density 34.655%

    No Known Activations