© 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. 51022
    Prev
    Next
    INDEX
    Explanations

    lover or lovers

    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
    Negative Logits
    arters
    -0.13
    uration
    -0.12
    ucer
    -0.12
    unos
    -0.11
    UME
    -0.11
    /OR
    -0.11
     quo
    -0.11
     poj
    -0.11
    eners
    -0.11
    egl
    -0.11
    POSITIVE LOGITS
    /part
    0.11
    ship
    0.10
    ries
    0.10
    /client
    0.10
    ships
    0.10
    SHIP
    0.10
    ably
    0.09
    able
    0.09
    ette
    0.08
    ick
    0.08
    Activations Density 0.004%

    No Known Activations