© 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. 46957
    Prev
    Next
    INDEX
    Explanations

    word parts like ste-ogenic or az-om

    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
     Knox
    -0.10
     moot
    -0.10
    ķìĿ¸
    -0.09
     Stark
    -0.09
     Wish
    -0.09
     sour
    -0.09
     hes
    -0.09
    outu
    -0.09
    ui
    -0.09
     dormant
    -0.09
    POSITIVE LOGITS
     assum
    0.11
     anyhow
    0.09
     attain
    0.09
    alian
    0.09
    emen
    0.08
     loosen
    0.08
     loft
    0.08
    -middle
    0.08
    iants
    0.08
     opt
    0.08
    Activations Density 0.001%

    No Known Activations