© 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. 26253
    Prev
    Next
    INDEX
    Explanations

    as an adjective or relative pronoun

    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
    alu
    -0.10
     felt
    -0.09
     Dorm
    -0.09
    ume
    -0.09
     magic
    -0.09
     Bra
    -0.09
     pretended
    -0.09
     shipping
    -0.09
    magic
    -0.09
     loyalty
    -0.09
    POSITIVE LOGITS
     fellow
    0.11
     colleagues
    0.11
     colleague
    0.10
     peers
    0.10
     prey
    0.10
     incompetent
    0.10
     Potential
    0.10
    irable
    0.09
     merely
    0.09
     expend
    0.09
    Activations Density 0.032%

    No Known Activations