© 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. 46991
    Prev
    Next
    INDEX
    Explanations

    newly acquired or used items

    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
     Hayes
    -0.10
     relevant
    -0.08
     attempting
    -0.08
    endi
    -0.08
     stitching
    -0.08
    arda
    -0.08
     Atlantic
    -0.08
     Totally
    -0.08
    732
    -0.08
     needed
    -0.08
    POSITIVE LOGITS
     newfound
    0.31
     acquired
    0.25
     newly
    0.22
     collected
    0.21
     obtained
    0.21
     gathered
    0.20
     recovered
    0.20
     captured
    0.20
     harvested
    0.19
     freshly
    0.19
    Activations Density 1.284%

    No Known Activations