© 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. 8470
    Prev
    Next
    INDEX
    Explanations

    you may

    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
    _Main
    -0.09
    ioc
    -0.09
    rix
    -0.09
     handmade
    -0.09
    ört
    -0.08
     impost
    -0.08
    est
    -0.08
    okie
    -0.08
     Cand
    -0.08
    CAC
    -0.08
    POSITIVE LOGITS
    isko
    0.10
     cgi
    0.10
     Gross
    0.08
    ucc
    0.08
    ku
    0.08
    uae
    0.08
     CGI
    0.08
    ross
    0.08
     Kerr
    0.07
     kepada
    0.07
    Activations Density 0.226%

    No Known Activations