© 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. 1430
    Prev
    Next
    INDEX
    Explanations

    Kara Sea, notifications, professionals

    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
    :first
    -0.10
    .nick
    -0.09
    urname
    -0.09
    /signup
    -0.08
    /buttons
    -0.08
     professionnel
    -0.08
    UserService
    -0.08
    iamond
    -0.08
    .moves
    -0.08
    /**/*.
    -0.08
    POSITIVE LOGITS
     billions
    0.08
     UNESCO
    0.07
     oficial
    0.07
    /reg
    0.07
     beef
    0.07
     levitra
    0.07
     tempting
    0.07
    ServiceProvider
    0.07
     dee
    0.07
     worldwide
    0.06
    Activations Density 6.997%

    No Known Activations