© 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. 4372
    Prev
    Next
    INDEX
    Explanations

    filmed scenes later

    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
    esterday
    -0.09
    -Smith
    -0.09
     yesterday
    -0.09
     tomorrow
    -0.09
     tales
    -0.09
     polar
    -0.08
     Sixth
    -0.08
     net
    -0.08
     Net
    -0.08
    "-
    -0.08
    POSITIVE LOGITS
    Later
    0.11
     later
    0.11
    imon
    0.11
     montage
    0.11
     scenes
    0.11
    itto
    0.11
     scene
    0.11
     Later
    0.11
    mont
    0.11
     filmed
    0.10
    Activations Density 0.132%

    No Known Activations