© 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. 32397
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    umm
    -0.11
     tread
    -0.09
     they
    -0.09
    -instance
    -0.09
     wanting
    -0.08
    íĬ
    -0.08
     horm
    -0.08
     runnable
    -0.08
     Gest
    -0.08
     either
    -0.08
    POSITIVE LOGITS
     distinction
    0.15
     distinctions
    0.15
     clarification
    0.14
     clar
    0.12
     clarified
    0.12
     clarify
    0.11
     primer
    0.11
     understanding
    0.11
     basics
    0.11
     basic
    0.11
    Activations Density 0.000%

    No Known Activations