© 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. 58372
    Prev
    Next
    INDEX
    Explanations

    vertex or vertices

    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
    -0.11
    hattan
    -0.10
    jo
    -0.10
    rat
    -0.10
    rd
    -0.09
    atics
    -0.09
    endencies
    -0.09
    ato
    -0.09
    ÑģÑĤи
    -0.09
    itty
    -0.09
    POSITIVE LOGITS
    ed
    0.15
    es
    0.13
    y
    0.12
    s
    0.10
    ing
    0.10
    esa
    0.10
    sched
    0.09
    oth
    0.09
    vol
    0.09
    ure
    0.08
    Activations Density 0.003%

    No Known Activations