© 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. 3833
    Prev
    Next
    INDEX
    Explanations

    assignment after underscore prefixed tokens

    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
    }elseif
    -0.10
    ÙĪÙĦ
    -0.10
    alker
    -0.10
     seals
    -0.09
     medi
    -0.09
    Ł
    -0.09
    yleft
    -0.09
    roph
    -0.09
    _mono
    -0.09
     Columns
    -0.09
    POSITIVE LOGITS
    po
    0.08
    ance
    0.07
     Boeh
    0.07
     Fres
    0.07
    pot
    0.07
    tern
    0.07
    ence
    0.07
    nip
    0.07
    Ĵ
    0.06
    0.06
    Activations Density 0.490%

    No Known Activations