© 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. 47945
    Prev
    Next
    INDEX
    Explanations

    in favor of

    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
    lon
    -0.11
    arent
    -0.11
     lon
    -0.11
     sto
    -0.11
    pps
    -0.10
     evacuated
    -0.10
    Vu
    -0.10
    cope
    -0.10
    crud
    -0.10
     Prospect
    -0.10
    POSITIVE LOGITS
     favor
    0.62
     favour
    0.57
     Favor
    0.52
     favors
    0.48
    favor
    0.47
     favorable
    0.45
     fav
    0.42
     favourable
    0.40
     unfavorable
    0.33
     favored
    0.32
    Activations Density 0.336%

    No Known Activations