© 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. 114652
    Prev
    Next
    INDEX
    Explanations

    flirt attraction conversation attraction

    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
     mourning
    -0.11
     mourn
    -0.11
     misc
    -0.11
     Countdown
    -0.11
     ceremonies
    -0.11
     plac
    -0.11
     ceremonial
    -0.10
     Benef
    -0.10
     blackmail
    -0.10
     Fus
    -0.10
    POSITIVE LOGITS
     flirt
    0.27
     flirting
    0.26
     smiles
    0.16
     convers
    0.16
     smiling
    0.15
     Conversation
    0.15
     conversation
    0.14
     flattering
    0.13
     attraction
    0.13
    Conversation
    0.13
    Activations Density 0.052%

    No Known Activations