© 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. 114392
    Prev
    Next
    INDEX
    Explanations

    "he is" or "he's"

    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
     partnering
    -0.11
     husbands
    -0.10
     husband
    -0.10
     betr
    -0.10
    isel
    -0.09
     partnered
    -0.09
     powerless
    -0.09
     partners
    -0.09
     insol
    -0.09
     partner
    -0.09
    POSITIVE LOGITS
    BN
    0.12
     quir
    0.11
     Gent
    0.11
    bis
    0.11
     qualities
    0.10
     compatible
    0.10
    bid
    0.10
     quirky
    0.10
     weekends
    0.10
    unicorn
    0.10
    Activations Density 0.018%

    No Known Activations