© 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-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 1614
    Prev
    Next
    INDEX
    Explanations

    making decisions about self and others

    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
     itemName
    -0.10
     nicknamed
    -0.10
    [].
    -0.10
    .TryParse
    -0.10
    :http
    -0.10
    pus
    -0.09
    luck
    -0.09
     parody
    -0.09
    \č↵
    -0.09
     orgy
    -0.09
    POSITIVE LOGITS
     things
    0.16
     others
    0.13
     something
    0.12
     whatever
    0.12
     stuff
    0.11
     everything
    0.11
     life
    0.11
     Others
    0.10
     decisions
    0.10
     loved
    0.10
    Activations Density 2.332%

    No Known Activations