© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 92545
    Prev
    Next
    INDEX
    Explanations

    possessive modifier of subsequent noun

    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
    Negative Logits
    dit
    -0.09
     gn
    -0.09
    342
    -0.09
    gart
    -0.09
    otte
    -0.09
    icker
    -0.09
     Raymond
    -0.09
    itu
    -0.08
    oria
    -0.08
    isp
    -0.08
    POSITIVE LOGITS
     approach
    0.22
     dealings
    0.17
     approaches
    0.16
     Approach
    0.16
    appro
    0.16
     choices
    0.15
     outlook
    0.15
     pursuits
    0.14
     wording
    0.14
    Appro
    0.13
    Activations Density 0.064%

    No Known Activations