© 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. 33624
    Prev
    Next
    INDEX
    Explanations

    gender or group counterparts

    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
    -vertical
    -0.11
     vog
    -0.11
    Dig
    -0.10
     unc
    -0.10
    atos
    -0.10
     little
    -0.10
     Oak
    -0.10
    /single
    -0.10
    .dtype
    -0.10
    vs
    -0.10
    POSITIVE LOGITS
     counterparts
    0.16
     counterpart
    0.16
     equivalents
    0.12
     equivalent
    0.11
     Bib
    0.10
     traditionally
    0.10
    —who
    0.09
     bib
    0.09
    icap
    0.08
     equival
    0.08
    Activations Density 0.227%

    No Known Activations