© 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. 58055
    Prev
    Next
    INDEX
    Explanations

    created date

    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
    ailer
    -0.09
     langs
    -0.08
    GRID
    -0.08
    ocs
    -0.08
    ahl
    -0.08
    zar
    -0.08
    atri
    -0.08
    EZ
    -0.07
    /_
    -0.07
     Eag
    -0.07
    POSITIVE LOGITS
    ehr
    0.10
     closest
    0.09
    iw
    0.09
    mes
    0.09
     оп
    0.08
    .);↵
    0.08
     Byron
    0.08
    Tower
    0.08
    Inverse
    0.08
     revers
    0.08
    Activations Density 0.001%

    No Known Activations