© 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. 91109
    Prev
    Next
    INDEX
    Explanations

    Dre, rey, rez, rex, ri, ro beginnings

    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
     outstanding
    -0.10
    /cms
    -0.09
    auc
    -0.09
     Eden
    -0.09
     Barb
    -0.09
    éĹ´
    -0.09
    abad
    -0.09
     Mehr
    -0.09
     conc
    -0.09
     assum
    -0.08
    POSITIVE LOGITS
    âĺħâĺħ
    0.09
    /design
    0.09
    scription
    0.09
     import
    0.08
    pper
    0.08
     Lyn
    0.08
    kowski
    0.08
     Pil
    0.08
    íĮ
    0.08
    rypt
    0.08
    Activations Density 0.011%

    No Known Activations