© 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. 6169
    Prev
    Next
    INDEX
    Explanations

    dating websites and services

    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
     unborn
    -0.10
     halluc
    -0.10
     goose
    -0.09
     Distrib
    -0.09
    producer
    -0.09
     Mothers
    -0.09
     aute
    -0.09
     Copp
    -0.09
     Circus
    -0.08
     reporters
    -0.08
    POSITIVE LOGITS
     dating
    0.41
     Dating
    0.37
     matchmaking
    0.33
     Tinder
    0.33
    dating
    0.31
    Dating
    0.31
     singles
    0.31
     profiles
    0.30
     datings
    0.29
     profile
    0.29
    Activations Density 0.315%

    No Known Activations