© 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. 4138
    Prev
    Next
    INDEX
    Explanations

    burn or burning

    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
    ago
    -0.09
     cle
    -0.08
    Forum
    -0.08
     vibration
    -0.08
     wedge
    -0.08
    ws
    -0.07
    dk
    -0.07
    ble
    -0.07
     imperson
    -0.07
    Bru
    -0.07
    POSITIVE LOGITS
     Burning
    0.14
     ember
    0.14
     burns
    0.14
    ished
    0.14
     Burns
    0.13
     flames
    0.13
     burn
    0.13
     Burn
    0.13
     burner
    0.13
     Flames
    0.12
    Activations Density 0.170%

    No Known Activations