© 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. 55471
    Prev
    Next
    INDEX
    Explanations

    considering

    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
    upt
    -0.14
     milit
    -0.11
    bai
    -0.10
    /////////////////////////////////////////////////////////////////////////////↵
    -0.10
    (ir
    -0.10
    -Ta
    -0.10
    .Quit
    -0.10
    /arm
    -0.10
    aea
    -0.10
    /mp
    -0.10
    POSITIVE LOGITS
     usually
    0.10
     sometime
    0.08
    gesch
    0.08
     normally
    0.08
     often
    0.07
    usually
    0.07
    often
    0.07
     fred
    0.07
    ony
    0.07
    aba
    0.07
    Activations Density 0.028%

    No Known Activations