© 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. 520
    Prev
    Next
    INDEX
    Explanations

    city names and country abbreviations

    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
    .createNew
    -0.10
    TimeString
    -0.09
    _gp
    -0.09
    KeyPressed
    -0.09
    sbin
    -0.09
    KeySpec
    -0.09
    -dd
    -0.09
     ['/
    -0.08
    Feedback
    -0.08
    -Encoding
    -0.08
    POSITIVE LOGITS
    lijah
    0.08
    ÑĢан
    0.07
     Labrador
    0.07
    .Reader
    0.07
    .setDefault
    0.07
    Arch
    0.07
    .fi
    0.07
    clipse
    0.06
    æģ¯
    0.06
     winters
    0.06
    Activations Density 6.118%

    No Known Activations