© 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. 47099
    Prev
    Next
    INDEX
    Explanations

    personally, myself, himself, herself

    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
    .tc
    -0.10
    wj
    -0.09
    ame
    -0.09
     aval
    -0.09
    vell
    -0.09
     outward
    -0.08
    -ul
    -0.08
    mr
    -0.08
     incidental
    -0.08
     approx
    -0.08
    POSITIVE LOGITS
     personally
    0.70
     Personally
    0.44
     directly
    0.37
     himself
    0.37
    Personally
    0.35
     manually
    0.34
     firsthand
    0.32
     herself
    0.31
     myself
    0.30
     personal
    0.29
    Activations Density 0.418%

    No Known Activations