© 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. 8519
    Prev
    Next
    INDEX
    Explanations

    eyes and their states

    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
    ter
    -0.09
    itude
    -0.09
    weigh
    -0.08
    es
    -0.08
     fro
    -0.08
    984
    -0.08
     Episcopal
    -0.08
    à¥įर
    -0.08
     spraying
    -0.08
    ñ
    -0.08
    POSITIVE LOGITS
    ight
    0.14
     stare
    0.12
    ockets
    0.12
     staring
    0.11
     sockets
    0.11
     eyes
    0.11
     stares
    0.11
    0.10
    blink
    0.10
     blinked
    0.10
    Activations Density 0.101%

    No Known Activations