© 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. 17937
    Prev
    Next
    INDEX
    Explanations

    prosthetics or heels

    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
     neatly
    -0.11
    alive
    -0.10
     Hed
    -0.10
    urat
    -0.09
     neat
    -0.09
     spilled
    -0.09
     alive
    -0.09
     vans
    -0.09
     flushed
    -0.09
     inde
    -0.08
    POSITIVE LOGITS
     stil
    0.19
     cumbersome
    0.17
     weights
    0.15
     weighted
    0.15
     hind
    0.13
     stiff
    0.13
     bulky
    0.13
     restrictive
    0.13
    -heavy
    0.13
     prost
    0.12
    Activations Density 0.049%

    No Known Activations