© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 58613
    Prev
    Next
    INDEX
    Explanations

    take example reference

    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
     scen
    -0.10
     wrap
    -0.09
    Wrap
    -0.09
     rop
    -0.09
     Downing
    -0.09
    elon
    -0.09
    iple
    -0.09
     cre
    -0.09
    esthetic
    -0.09
    tr
    -0.08
    POSITIVE LOGITS
     example
    0.09
    nyder
    0.08
    ej
    0.08
    rez
    0.08
     XK
    0.08
    éri
    0.08
    odb
    0.08
    ilik
    0.07
    appen
    0.07
     symbols
    0.07
    Activations Density 0.054%

    No Known Activations