© 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. 54649
    Prev
    Next
    INDEX
    Explanations

    assignment or object definition syntax

    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
     kenn
    -0.07
     getattr
    -0.07
    osc
    -0.07
     ambit
    -0.07
    emachine
    -0.07
    Helpers
    -0.06
    irs
    -0.06
     fus
    -0.06
     rematch
    -0.06
     WLAN
    -0.06
    POSITIVE LOGITS
     Vid
    0.10
    berra
    0.10
     crushed
    0.10
    rium
    0.10
    cean
    0.10
     extracted
    0.09
    tat
    0.09
    andalone
    0.09
     convent
    0.09
    ensi
    0.09
    Activations Density 0.004%

    No Known Activations