© 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. 50382
    Prev
    Next
    INDEX
    Explanations

    moral disagreement or ethical questions

    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
     tangible
    -0.12
     acad
    -0.11
     validations
    -0.11
    ponder
    -0.10
     contradictions
    -0.10
     subconscious
    -0.09
     dispro
    -0.09
     positioning
    -0.09
     measurable
    -0.09
     absol
    -0.09
    POSITIVE LOGITS
     qua
    0.21
     morally
    0.19
     redes
    0.18
     prima
    0.17
     Kant
    0.17
     instantiate
    0.16
     elimin
    0.15
     moral
    0.15
     presup
    0.15
     instantiated
    0.14
    Activations Density 1.482%

    No Known Activations