© 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. 57953
    Prev
    Next
    INDEX
    Explanations

    .ssl, .user, .app, .ws, .show, .allow, .rb

    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
    oki
    -0.09
    []{↵
    -0.08
     concess
    -0.08
    resenter
    -0.07
     devast
    -0.07
     heter
    -0.07
     rather
    -0.07
     cand
    -0.07
    uel
    -0.07
    omat
    -0.07
    POSITIVE LOGITS
     sund
    0.11
    grounds
    0.09
    zer
    0.09
     Among
    0.09
    rey
    0.09
    oeff
    0.08
    lik
    0.08
    ãģĹãģĭ
    0.08
    mand
    0.08
    _use
    0.08
    Activations Density 0.056%

    No Known Activations