© 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. 4234
    Prev
    Next
    INDEX
    Explanations

    email to, address, this

    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
     mailing
    -0.11
     mail
    -0.10
    Mail
    -0.10
     mailed
    -0.09
    wick
    -0.09
     email
    -0.09
    lick
    -0.09
    mail
    -0.09
    /mail
    -0.08
     emails
    -0.08
    POSITIVE LOGITS
    .mime
    0.09
    æĹı
    0.09
    thon
    0.09
     {[
    0.09
    ¯
    0.09
    modo
    0.09
    etter
    0.08
     plac
    0.08
    tica
    0.08
    .utils
    0.08
    Activations Density 0.051%

    No Known Activations