© 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. 6894
    Prev
    Next
    INDEX
    Explanations

    endearment expressions

    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
     sir
    -0.11
     "...
    -0.09
     Creed
    -0.09
    "She
    -0.09
     prostate
    -0.09
    heim
    -0.09
     Arrival
    -0.09
    lac
    -0.09
     reluctant
    -0.09
     Unable
    -0.09
    POSITIVE LOGITS
     gigg
    0.14
    "Oh
    0.13
     laugh
    0.13
    “Oh
    0.13
     darling
    0.13
     oh
    0.13
     naughty
    0.12
     laughed
    0.12
    Laugh
    0.12
     laughter
    0.12
    Activations Density 0.030%

    No Known Activations