© 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. 50282
    Prev
    Next
    INDEX
    Explanations

    escorts and prostitution

    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
     Ard
    -0.12
     Sporting
    -0.11
     specifier
    -0.11
     bored
    -0.10
     Tick
    -0.10
     Crate
    -0.10
     Saud
    -0.10
     locals
    -0.09
     revolving
    -0.09
     Destruction
    -0.09
    POSITIVE LOGITS
     escorts
    0.24
     Escorts
    0.21
     escort
    0.18
     backpage
    0.18
     escorted
    0.17
     Escort
    0.16
    Escort
    0.15
     prostitution
    0.13
     esc
    0.13
     escorte
    0.12
    Activations Density 0.002%

    No Known Activations