© 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. 33973
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by temporal or possession words

    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
    alu
    -0.09
     haul
    -0.09
     surfaces
    -0.08
    friend
    -0.08
     trophies
    -0.08
     sire
    -0.08
    unting
    -0.08
    ople
    -0.08
     pg
    -0.08
     fus
    -0.08
    POSITIVE LOGITS
     favor
    0.19
     midst
    0.19
     haste
    0.19
     favour
    0.19
     entirety
    0.18
     stead
    0.18
     absence
    0.16
     wake
    0.15
    quest
    0.14
     eag
    0.13
    Activations Density 0.093%

    No Known Activations