© 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. 57436
    Prev
    Next
    INDEX
    Explanations

    source code attributes

    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
    athi
    -0.10
    /Table
    -0.09
     Johnston
    -0.09
    ufs
    -0.09
    );;↵
    -0.09
     Saved
    -0.09
    /apt
    -0.09
    advance
    -0.09
    è®
    -0.08
    /model
    -0.08
    POSITIVE LOGITS
    ourn
    0.08
     undone
    0.08
    andan
    0.08
    atri
    0.07
    ìĸ
    0.07
    Offline
    0.07
    /connect
    0.07
     obt
    0.07
     Choices
    0.07
    fault
    0.07
    Activations Density 0.001%

    No Known Activations