© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 26846
    Prev
    Next
    INDEX
    Explanations

    ladies and gentlemen

    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
     parental
    -0.09
     absorbing
    -0.08
     childhood
    -0.08
    hell
    -0.08
     grandparents
    -0.08
    erras
    -0.08
    dater
    -0.08
     parent
    -0.07
     oma
    -0.07
     Homepage
    -0.07
    POSITIVE LOGITS
     gentleman
    0.21
     gentlemen
    0.21
     lady
    0.17
    Lady
    0.17
     Lady
    0.17
     ladies
    0.14
     Gaga
    0.13
     Ladies
    0.13
     Gentle
    0.12
     knights
    0.11
    Activations Density 0.028%

    No Known Activations