© 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. 90067
    Prev
    Next
    INDEX
    Explanations

    curse, cursed, curses

    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
     Mundo
    -0.09
    nie
    -0.09
    ismo
    -0.08
    lining
    -0.08
     doubtful
    -0.08
    SK
    -0.08
    iates
    -0.08
    mue
    -0.08
    ondon
    -0.08
    ald
    -0.08
    POSITIVE LOGITS
    edly
    0.17
    eds
    0.14
     curse
    0.13
     curses
    0.13
    ield
    0.12
     cursed
    0.12
    breaking
    0.12
    ingly
    0.12
    fully
    0.12
    indow
    0.12
    Activations Density 0.005%

    No Known Activations