© 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. 48295
    Prev
    Next
    INDEX
    Explanations

    dating exclusively

    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
     worm
    -0.09
    andal
    -0.09
     Typed
    -0.08
    flat
    -0.08
    ç«Ļ
    -0.08
    otype
    -0.08
     Bair
    -0.08
    ced
    -0.08
    ross
    -0.08
    anch
    -0.08
    POSITIVE LOGITS
     domestically
    0.16
     dating
    0.15
     relationships
    0.15
     Relationships
    0.14
     Dating
    0.14
     DIY
    0.14
     amateur
    0.13
     civilian
    0.13
     domestic
    0.13
     amateurs
    0.13
    Activations Density 0.016%

    No Known Activations