© 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. 30856
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns after certain 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
    Not in Any Lists

    No Comments

    Negative Logits
    folio
    -0.10
    /star
    -0.10
     squat
    -0.10
     McGregor
    -0.10
     Tail
    -0.10
    bron
    -0.10
    Sad
    -0.10
    antro
    -0.10
     beh
    -0.10
    acier
    -0.10
    POSITIVE LOGITS
     breasts
    0.11
    ASI
    0.09
     emerging
    0.08
     asymmetric
    0.08
     soft
    0.08
     ribs
    0.08
    ERIC
    0.07
     belt
    0.07
     Johnston
    0.07
    ETA
    0.07
    Activations Density 0.012%

    No Known Activations