© 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. 31496
    Prev
    Next
    INDEX
    Explanations

    Lockett, monolog, enron

    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
     incon
    -0.05
    elo
    -0.05
    oin
    -0.05
     Skinny
    -0.05
    bout
    -0.05
     and
    -0.05
    571
    -0.05
     lup
    -0.05
    zh
    -0.04
    ther
    -0.04
    POSITIVE LOGITS
    ĥĿ
    0.12
     recru
    0.12
    ottom
    0.11
     traj
    0.11
     consum
    0.11
    iffies
    0.11
     goodies
    0.11
    (Call
    0.11
     pcl
    0.11
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.11
    Activations Density 1.172%

    No Known Activations