© 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. 57227
    Prev
    Next
    INDEX
    Explanations

    ng-controller="

    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
    opia
    -0.11
    æĿĥ
    -0.10
    noch
    -0.10
    (rep
    -0.09
    Programming
    -0.09
    auty
    -0.09
     Programm
    -0.09
    amac
    -0.09
    bread
    -0.09
    NEWS
    -0.09
    POSITIVE LOGITS
    haft
    0.09
     belie
    0.08
     simult
    0.07
    crew
    0.07
    /Public
    0.07
     sess
    0.07
    inidad
    0.07
    urple
    0.07
     Roths
    0.07
     mono
    0.07
    Activations Density 0.006%

    No Known Activations