© 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. 15709
    Prev
    Next
    INDEX
    Explanations

    easily, safely, or reliably

    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
    ewan
    -0.11
     kunnen
    -0.11
     unnecessarily
    -0.10
     poder
    -0.10
     pouvoir
    -0.10
    ghi
    -0.10
     eagerly
    -0.10
     inevitably
    -0.10
     Tall
    -0.10
    orda
    -0.10
    POSITIVE LOGITS
     easily
    0.36
     Easily
    0.28
     anytime
    0.20
     safely
    0.18
     feas
    0.18
     reliably
    0.17
     eas
    0.17
     comfortably
    0.17
    à¹Ħ
    0.17
     effortlessly
    0.16
    Activations Density 0.387%

    No Known Activations