© 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-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 3747
    Prev
    Next
    INDEX
    Explanations

    ethics and morals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Met
    -0.08
     Thumb
    -0.08
     light
    -0.08
    cona
    -0.07
    enty
    -0.07
    Anonymous
    -0.07
    MetaData
    -0.07
    raf
    -0.07
     Roc
    -0.07
    DIR
    -0.07
    POSITIVE LOGITS
     morally
    0.13
     moral
    0.12
     morals
    0.12
     ethical
    0.12
    /values
    0.11
     Moral
    0.11
    aqu
    0.11
     deeds
    0.11
     conduct
    0.11
    iera
    0.11
    Activations Density 0.166%

    No Known Activations