© 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. 55208
    Prev
    Next
    INDEX
    Explanations

    reward for achievement or good behavior

    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
     sanity
    -0.07
    egot
    -0.07
     boto
    -0.07
     fallback
    -0.06
     magnetic
    -0.06
     Sanity
    -0.06
     dumped
    -0.06
     unfair
    -0.06
     vulner
    -0.06
    uma
    -0.06
    POSITIVE LOGITS
     reward
    0.17
     rewarded
    0.16
     Reward
    0.16
     commend
    0.15
     rewards
    0.14
     Rewards
    0.14
     rewarding
    0.12
    Reward
    0.12
     Correct
    0.12
     praise
    0.12
    Activations Density 0.113%

    No Known Activations