© 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. 46385
    Prev
    Next
    INDEX
    Explanations

    specifying context after 'of'

    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
     strife
    -0.10
     differing
    -0.10
     --↵↵
    -0.10
     Wheat
    -0.09
     Glad
    -0.09
    ibs
    -0.09
     varying
    -0.09
     imagery
    -0.09
     dare
    -0.09
     Gabri
    -0.09
    POSITIVE LOGITS
     equipments
    0.10
    /front
    0.10
    lij
    0.09
    iance
    0.09
     optionally
    0.09
    774
    0.09
     advises
    0.09
     respectively
    0.09
    jad
    0.09
    etro
    0.08
    Activations Density 0.467%

    No Known Activations