© 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. 92153
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns or contractions

    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
     thereafter
    -0.10
     bella
    -0.10
    gv
    -0.09
     Nd
    -0.09
     (!!
    -0.09
     stylist
    -0.09
    -performance
    -0.09
     Md
    -0.09
    wcs
    -0.09
    elly
    -0.09
    POSITIVE LOGITS
     Dul
    0.10
     ours
    0.10
     theirs
    0.09
     namely
    0.09
     swo
    0.08
     yours
    0.08
    ulet
    0.08
    888
    0.08
    -dominated
    0.08
    aupt
    0.08
    Activations Density 0.358%

    No Known Activations