© 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. 29396
    Prev
    Next
    INDEX
    Explanations

    Lawyers and firm names

    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
     swore
    -0.10
     UNIVERS
    -0.10
     Mellon
    -0.10
    agents
    -0.10
     Agent
    -0.10
     stump
    -0.09
     rentals
    -0.09
    AGENT
    -0.09
     contracted
    -0.09
    SMART
    -0.09
    POSITIVE LOGITS
     defenses
    0.14
     defending
    0.13
     defend
    0.12
     aggressively
    0.12
     defense
    0.12
     defended
    0.12
     DUI
    0.12
     defends
    0.11
    Defense
    0.11
     Att
    0.11
    Activations Density 2.091%

    No Known Activations