© 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. 49151
    Prev
    Next
    INDEX
    Explanations

    Court filings and legal acronyms

    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
     Ember
    -0.09
    otate
    -0.09
     Jesus
    -0.09
     Alfred
    -0.09
     Flask
    -0.08
     Dont
    -0.08
     Miguel
    -0.08
     Django
    -0.08
     Richard
    -0.07
     William
    -0.07
    POSITIVE LOGITS
     Voor
    0.11
     Families
    0.10
    Expert
    0.10
    urn
    0.10
     Heb
    0.10
     Peek
    0.10
     tarn
    0.10
     Wass
    0.10
     MSI
    0.10
    599
    0.09
    Activations Density 0.095%

    No Known Activations