© 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. 92219
    Prev
    Next
    INDEX
    Explanations

    precipitation method

    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
     Aff
    -0.08
     LG
    -0.08
     pr
    -0.07
     Yankee
    -0.07
     constr
    -0.07
    rey
    -0.07
     Clar
    -0.07
     Suff
    -0.07
     conven
    -0.07
     Cadillac
    -0.07
    POSITIVE LOGITS
     risky
    0.12
     detriment
    0.11
     slim
    0.11
     unfavorable
    0.11
    continued
    0.11
     improvised
    0.11
     Slim
    0.11
    endon
    0.11
    usto
    0.11
    dex
    0.11
    Activations Density 0.001%

    No Known Activations