© 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. 4585
    Prev
    Next
    INDEX
    Explanations

    and other conjunctions

    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
    anje
    -0.12
    iek
    -0.10
    çĻ
    -0.10
    _bundle
    -0.10
    uisse
    -0.10
    gom
    -0.10
     Hall
    -0.09
     actually
    -0.09
    č↵↵
    -0.09
    istance
    -0.09
    POSITIVE LOGITS
    .gdx
    0.09
    ses
    0.08
    minus
    0.07
    dad
    0.07
    pace
    0.07
    .linkedin
    0.07
     Tour
    0.07
    /doc
    0.07
    /XML
    0.07
    uckle
    0.07
    Activations Density 0.130%

    No Known Activations