© 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. 56161
    Prev
    Next
    INDEX
    Explanations

    integer?

    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
    ifest
    -0.12
    owi
    -0.10
     tiny
    -0.10
     cron
    -0.09
    bei
    -0.09
     Cooper
    -0.09
    _mut
    -0.09
    -repeat
    -0.09
    ()",
    -0.09
    /devices
    -0.09
    POSITIVE LOGITS
     hyp
    0.09
    dam
    0.09
     wakes
    0.07
    loff
    0.07
     meg
    0.07
    onde
    0.07
     Pit
    0.07
     suits
    0.07
     gust
    0.06
     Pav
    0.06
    Activations Density 0.002%

    No Known Activations