© 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. 3721
    Prev
    Next
    INDEX
    Explanations

    function definitions

    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
     bez
    -0.09
     opp
    -0.09
    prox
    -0.08
     chatt
    -0.08
    Ob
    -0.08
    {o
    -0.08
     Bed
    -0.08
    202
    -0.08
     discreet
    -0.07
     Ob
    -0.07
    POSITIVE LOGITS
     [âĢ¦]
    0.11
    [âĢ¦]
    0.10
     Corporate
    0.10
     Whilst
    0.09
    én
    0.09
    rus
    0.09
     favoured
    0.09
     "\""
    0.09
     â
    0.09
     [...]
    0.09
    Activations Density 0.614%

    No Known Activations