© 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. 47472
    Prev
    Next
    INDEX
    Explanations

    protecting from damage or contamination

    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
    ernet
    -0.10
     withholding
    -0.09
     restrain
    -0.09
     repay
    -0.08
    CPP
    -0.08
     Reyn
    -0.08
    оÑī
    -0.08
     inland
    -0.08
     withhold
    -0.08
    -re
    -0.08
    POSITIVE LOGITS
     damage
    0.20
     damaged
    0.16
     scratches
    0.16
     damages
    0.15
     dust
    0.15
     scratched
    0.14
     accidentally
    0.14
     Damage
    0.14
     tam
    0.14
     DAMAGE
    0.14
    Activations Density 0.128%

    No Known Activations