© 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. 6838
    Prev
    Next
    INDEX
    Explanations

    court, appeal, license, copyright

    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
     Bert
    -0.10
    erta
    -0.10
     Mund
    -0.09
     sc
    -0.09
     fatt
    -0.09
     Dum
    -0.09
    asel
    -0.09
     surf
    -0.09
    thin
    -0.09
     Javier
    -0.09
    POSITIVE LOGITS
     Geh
    0.10
     hung
    0.10
    âħ
    0.09
    à¸Ń
    0.08
    olvency
    0.08
     stylist
    0.08
     succeeding
    0.08
     Svens
    0.08
    ror
    0.08
     circa
    0.08
    Activations Density 0.004%

    No Known Activations