© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114075
    Prev
    Next
    INDEX
    Explanations

    crime and legal consequences

    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
     lawsuits
    -0.11
     unethical
    -0.11
     lawful
    -0.11
    infos
    -0.11
     premature
    -0.11
     Zuk
    -0.11
     lawsuit
    -0.11
    Suit
    -0.10
     illeg
    -0.10
     McMaster
    -0.10
    POSITIVE LOGITS
     aggrav
    0.15
     motive
    0.15
     accomp
    0.14
     motives
    0.13
     remorse
    0.12
     repeat
    0.12
     Mot
    0.11
     minor
    0.11
     motivation
    0.10
     Minor
    0.10
    Activations Density 0.442%

    No Known Activations