© 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. 55339
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    st
    -0.09
    ese
    -0.09
    ish
    -0.08
    edo
    -0.08
    otti
    -0.08
     Rein
    -0.08
     rich
    -0.08
    еж
    -0.08
    ery
    -0.08
    ers
    -0.08
    POSITIVE LOGITS
    .mo
    0.09
    chema
    0.09
    inode
    0.08
     mour
    0.08
    noc
    0.08
     cra
    0.08
     facts
    0.08
    toy
    0.08
    åı£
    0.08
    illon
    0.08
    Activations Density 0.010%

    No Known Activations