© 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. 116559
    Prev
    Next
    INDEX
    Explanations

    star-crossed romance or disapproval

    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
     redesign
    -0.10
     residual
    -0.10
    advert
    -0.09
     inadvertently
    -0.09
     synonymous
    -0.09
     correlated
    -0.09
     cath
    -0.09
    DED
    -0.09
     PSD
    -0.09
     flick
    -0.08
    POSITIVE LOGITS
     interracial
    0.22
     Romeo
    0.20
     marrying
    0.20
     forbidden
    0.19
     Interracial
    0.18
     romance
    0.18
     forbid
    0.17
     pairing
    0.17
     prohib
    0.16
     approvals
    0.16
    Activations Density 0.093%

    No Known Activations