© 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. 16195
    Prev
    Next
    INDEX
    Explanations

    dating and relationships

    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
     bac
    -0.10
    ppo
    -0.10
     exert
    -0.10
     SAL
    -0.09
    ,âĢ¦
    -0.09
     honeymoon
    -0.09
    ).'
    -0.09
     Clim
    -0.09
    caps
    -0.09
    noop
    -0.09
    POSITIVE LOGITS
     dating
    0.21
     Dating
    0.19
     dates
    0.19
     date
    0.19
     Dates
    0.17
     Date
    0.17
    Dating
    0.17
    date
    0.15
     DATE
    0.15
    -date
    0.15
    Activations Density 0.058%

    No Known Activations