© 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. 18724
    Prev
    Next
    INDEX
    Explanations

    possessive nouns and pronouns

    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
     Bucc
    -0.09
     ceilings
    -0.09
    otto
    -0.09
     inher
    -0.08
     nature
    -0.08
     elevator
    -0.08
    cers
    -0.08
     borders
    -0.08
    ho
    -0.08
    banana
    -0.08
    POSITIVE LOGITS
     purse
    0.13
     belongings
    0.13
     abandoned
    0.11
     discarded
    0.11
     original
    0.11
     Lub
    0.10
     beware
    0.10
     luggage
    0.10
     comp
    0.10
     clothes
    0.10
    Activations Density 0.024%

    No Known Activations