© 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. 4101
    Prev
    Next
    INDEX
    Explanations

    posted on or by

    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
    oso
    -0.08
     dig
    -0.08
     Valent
    -0.07
    -0.07
    cko
    -0.07
     accredited
    -0.07
     grav
    -0.07
    imming
    -0.07
     punch
    -0.07
    erness
    -0.07
    POSITIVE LOGITS
    pone
    0.12
    gi
    0.10
     Lig
    0.10
     incon
    0.10
    pon
    0.10
     toll
    0.09
    ]↵↵↵↵
    0.09
     acceleration
    0.09
    etten
    0.09
    icked
    0.09
    Activations Density 0.126%

    No Known Activations