© 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. 49699
    Prev
    Next
    INDEX
    Explanations

    determiners followed by unique noun phrases

    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
     versions
    -0.11
    olvers
    -0.11
    otte
    -0.11
     helicopt
    -0.11
     blasted
    -0.11
     Readers
    -0.11
     characterization
    -0.11
     incarn
    -0.11
     darn
    -0.11
     gord
    -0.11
    POSITIVE LOGITS
     specially
    0.18
     unique
    0.17
     durable
    0.16
     robust
    0.16
     innovative
    0.16
     integrated
    0.15
     generous
    0.15
     flexible
    0.15
     versatile
    0.14
     powerful
    0.14
    Activations Density 0.412%

    No Known Activations