© 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. 112014
    Prev
    Next
    INDEX
    Explanations

    learning curve

    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
     imminent
    -0.09
    lox
    -0.09
    linger
    -0.09
    rai
    -0.09
    rage
    -0.09
    AFE
    -0.09
    guns
    -0.09
     emptied
    -0.08
    ngr
    -0.08
     verified
    -0.08
    POSITIVE LOGITS
     learning
    0.38
     Learning
    0.32
    learning
    0.31
    Learning
    0.30
    -learning
    0.27
     figuring
    0.26
     learns
    0.26
     learn
    0.26
     trial
    0.24
     experimentation
    0.22
    Activations Density 0.198%

    No Known Activations