© 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. 91446
    Prev
    Next
    INDEX
    Explanations

    jude, judy, jc, cj, pj

    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
     peel
    -0.10
    altar
    -0.09
    mate
    -0.08
     Trash
    -0.08
    ivet
    -0.08
    DDL
    -0.08
    alion
    -0.08
     Maher
    -0.08
    ria
    -0.08
     Cri
    -0.08
    POSITIVE LOGITS
     Judy
    0.20
     Jude
    0.13
     BJ
    0.13
    udy
    0.13
     Jays
    0.12
     Rudy
    0.12
    JC
    0.12
    cj
    0.12
     prejud
    0.11
     PJ
    0.11
    Activations Density 0.001%

    No Known Activations