© 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. 3561
    Prev
    Next
    INDEX
    Explanations

    XML tags and 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
     Burton
    -0.10
     Rib
    -0.10
     Yates
    -0.09
    олÑĮ
    -0.09
    ils
    -0.09
     Butter
    -0.08
     prospect
    -0.08
    ellow
    -0.08
    nell
    -0.08
    agr
    -0.08
    POSITIVE LOGITS
     thereof
    0.09
     gears
    0.07
    lan
    0.07
     Flo
    0.07
    elves
    0.07
    citation
    0.07
    azzi
    0.07
     wings
    0.07
     imm
    0.06
    ira
    0.06
    Activations Density 0.140%

    No Known Activations