© 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. 58311
    Prev
    Next
    INDEX
    Explanations

    the word with

    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
    ffer
    -0.10
    STA
    -0.09
    rek
    -0.09
    ris
    -0.09
     Recursive
    -0.09
    .decor
    -0.09
    /File
    -0.08
     cris
    -0.08
     gee
    -0.08
    oust
    -0.08
    POSITIVE LOGITS
    cy
    0.09
     reserve
    0.09
     Spare
    0.09
     raw
    0.08
     bare
    0.08
    reserve
    0.08
     brush
    0.08
    Raw
    0.08
     spare
    0.07
     Omni
    0.07
    Activations Density 0.042%

    No Known Activations