© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 3730
    Prev
    Next
    INDEX
    Explanations

    positive emotions and affections

    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
     Fucking
    -0.20
     fucking
    -0.20
     miserable
    -0.17
     piss
    -0.17
     fucked
    -0.16
     pissed
    -0.16
     bitch
    -0.16
    Fuck
    -0.16
     porn
    -0.16
     Fuck
    -0.15
    POSITIVE LOGITS
     smiling
    0.22
     adorable
    0.22
     smiles
    0.20
     heartfelt
    0.18
     romance
    0.18
     affection
    0.18
     smile
    0.18
     warmly
    0.18
     smiled
    0.18
     gracefully
    0.18
    Activations Density 0.351%

    No Known Activations