© 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. 47144
    Prev
    Next
    INDEX
    Explanations

    sweet female lover

    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
     blk
    -0.10
     RAT
    -0.10
     cer
    -0.10
     POT
    -0.10
     hob
    -0.10
     Jonas
    -0.09
     bef
    -0.09
     Routine
    -0.09
     routine
    -0.09
     conscience
    -0.09
    POSITIVE LOGITS
     beloved
    0.13
     Lover
    0.11
     Romeo
    0.10
     lover
    0.10
     darling
    0.10
     Heath
    0.10
     sweetheart
    0.10
     Darling
    0.10
     Ner
    0.10
     eros
    0.09
    Activations Density 0.203%

    No Known Activations