© 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. 28375
    Prev
    Next
    INDEX
    Explanations

    most / superlative adjectives or adverbs

    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
     Vict
    -0.11
     mul
    -0.09
    roz
    -0.09
     irreversible
    -0.09
    ias
    -0.09
     always
    -0.09
    acha
    -0.08
    always
    -0.08
    ugins
    -0.08
     rer
    -0.08
    POSITIVE LOGITS
     largest
    0.28
     longest
    0.27
     greatest
    0.23
     fastest
    0.22
     finest
    0.22
     Largest
    0.21
     biggest
    0.21
     unprecedented
    0.21
    iest
    0.21
     richest
    0.21
    Activations Density 0.267%

    No Known Activations