© 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. 61747
    Prev
    Next
    INDEX
    Explanations

    status codes OK SUCCESS 200

    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
     Rak
    -0.11
     thankfully
    -0.09
     untouched
    -0.09
     reput
    -0.09
     chances
    -0.08
     luckily
    -0.08
     Pill
    -0.08
     reputation
    -0.08
     Reputation
    -0.08
     Provided
    -0.08
    POSITIVE LOGITS
     creatively
    0.09
     combined
    0.09
     creativity
    0.09
    antic
    0.09
    isko
    0.08
    AY
    0.08
    ¨
    0.08
    ay
    0.08
     relay
    0.08
    å¡
    0.08
    Activations Density 0.020%

    No Known Activations