© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 56534
    Prev
    Next
    INDEX
    Explanations

    .author or .api

    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
     hydro
    -0.09
    ak
    -0.08
     Gotham
    -0.08
    öt
    -0.08
     Valent
    -0.08
    ges
    -0.08
    .fc
    -0.08
     Bale
    -0.08
    RTL
    -0.08
     World
    -0.08
    POSITIVE LOGITS
    izations
    0.09
    ãĤı
    0.08
     seper
    0.08
     Git
    0.08
     Enum
    0.08
    discard
    0.08
    wner
    0.08
    thing
    0.08
     penc
    0.08
    ABILITY
    0.08
    Activations Density 0.001%

    No Known Activations