© 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. 58467
    Prev
    Next
    INDEX
    Explanations

    citations with identifier prefixes

    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
    i
    -0.13
    a
    -0.12
    o
    -0.12
    iT
    -0.09
    vang
    -0.09
    aug
    -0.08
    añ
    -0.08
    lyn
    -0.08
    ORM
    -0.07
    .OS
    -0.07
    POSITIVE LOGITS
    er
    0.21
    ER
    0.10
    erne
    0.10
    erer
    0.10
    ĵåIJį
    0.09
    ferences
    0.09
    ting
    0.09
    ing
    0.09
     stiff
    0.09
     descent
    0.09
    Activations Density 0.002%

    No Known Activations