© 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. 47013
    Prev
    Next
    INDEX
    Explanations

    names in legal proceedings

    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
     muse
    -0.08
     sire
    -0.08
     reli
    -0.08
     weaponry
    -0.08
     puss
    -0.07
     ="";↵
    -0.07
     signature
    -0.07
     zap
    -0.07
     repr
    -0.07
     TBD
    -0.07
    POSITIVE LOGITS
     allegedly
    0.15
     disgr
    0.15
     implicated
    0.15
     innoc
    0.14
     alleged
    0.14
     Plaintiff
    0.13
     damning
    0.13
     whistleblower
    0.12
     misconduct
    0.12
     allegations
    0.12
    Activations Density 1.055%

    No Known Activations