© 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. 57542
    Prev
    Next
    INDEX
    Explanations

    For ... see:

    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
     wherever
    -0.08
     Chic
    -0.08
    emy
    -0.08
     until
    -0.07
    ahr
    -0.07
     Vib
    -0.07
     Gos
    -0.07
    ....↵↵
    -0.07
    atic
    -0.07
     trend
    -0.07
    POSITIVE LOGITS
    baugh
    0.11
     rom
    0.09
    ffd
    0.09
    ymous
    0.09
    lik
    0.09
    erah
    0.09
    .Formatter
    0.09
    decor
    0.09
    ):-
    0.09
    Occurrences
    0.08
    Activations Density 0.004%

    No Known Activations