© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 55614
    Prev
    Next
    INDEX
    Explanations

    comparison operators

    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
     Voll
    -0.08
     Skyl
    -0.08
    insky
    -0.08
    hip
    -0.08
    hell
    -0.08
     bri
    -0.08
    iad
    -0.08
    -not
    -0.08
    Suffix
    -0.08
    iani
    -0.08
    POSITIVE LOGITS
    icts
    0.11
    oba
    0.10
    oled
    0.09
    /thread
    0.09
    aac
    0.09
     compr
    0.09
    edo
    0.09
    WI
    0.08
     ../../
    0.08
    stm
    0.08
    Activations Density 0.009%

    No Known Activations