© 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. 54363
    Prev
    Next
    INDEX
    Explanations

    judge 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
    -0.11
    uada
    -0.10
    اد
    -0.09
    itime
    -0.09
    uga
    -0.09
    utta
    -0.08
     ADA
    -0.08
    fas
    -0.08
    ivre
    -0.08
    igy
    -0.08
    POSITIVE LOGITS
    al
    0.11
    antly
    0.10
    ova
    0.10
    ous
    0.10
    ship
    0.10
    uito
    0.09
    ator
    0.09
     pr
    0.09
    ANT
    0.09
    dispose
    0.09
    Activations Density 0.007%

    No Known Activations