© 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. 91681
    Prev
    Next
    INDEX
    Explanations

    special characters or numbers

    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
     penned
    -0.10
    appen
    -0.10
     Woody
    -0.10
    reu
    -0.09
    gd
    -0.08
    enia
    -0.08
    ipa
    -0.08
     padd
    -0.08
    packed
    -0.08
    izzie
    -0.08
    POSITIVE LOGITS
     Arte
    0.11
     magically
    0.10
    holm
    0.10
     Venez
    0.09
    Ars
    0.09
     forthcoming
    0.09
     installation
    0.09
    ocos
    0.09
     administr
    0.09
     Ih
    0.09
    Activations Density 0.001%

    No Known Activations