© 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. 7721
    Prev
    Next
    INDEX
    Explanations

    consequences and improvement

    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
     torture
    -0.13
     ruth
    -0.12
     punishment
    -0.11
     punishments
    -0.11
     ruthless
    -0.11
     punishing
    -0.11
     punish
    -0.11
     unconventional
    -0.11
     overhead
    -0.10
     cruel
    -0.10
    POSITIVE LOGITS
     behavior
    0.13
     correction
    0.13
     behavioral
    0.12
     corrections
    0.12
     wrongdoing
    0.11
     behaviors
    0.11
     spiritually
    0.11
     improvement
    0.11
     remorse
    0.11
     deter
    0.11
    Activations Density 0.085%

    No Known Activations