© 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. 14910
    Prev
    Next
    INDEX
    Explanations

    superlative adjectives with positive or negative context

    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
     latest
    -0.11
    ipi
    -0.10
     uncommon
    -0.09
     unprecedented
    -0.09
     classics
    -0.09
    latest
    -0.09
    oday
    -0.09
    iban
    -0.09
     newest
    -0.09
     unheard
    -0.09
    POSITIVE LOGITS
     sentient
    0.10
     moment
    0.10
     anything
    0.10
     momentos
    0.10
     beings
    0.10
    azzi
    0.10
     television
    0.09
     moments
    0.09
     narrowly
    0.09
     Sporting
    0.09
    Activations Density 0.151%

    No Known Activations