© 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. 4123
    Prev
    Next
    INDEX
    Explanations

    table schema descriptions

    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
     none
    -0.08
     prone
    -0.08
     multiply
    -0.08
     Wayne
    -0.07
    ego
    -0.07
    /fast
    -0.07
     Huck
    -0.07
    gem
    -0.07
    use
    -0.07
     mist
    -0.07
    POSITIVE LOGITS
     Budd
    0.11
     Darling
    0.11
     Remarks
    0.10
     #↵
    0.10
    Unnamed
    0.10
    malink
    0.09
    ($)
    0.09
    thin
    0.09
    ipe
    0.09
    empl
    0.09
    Activations Density 0.162%

    No Known Activations