© 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. 8612
    Prev
    Next
    INDEX
    Explanations

    declaration keywords like final or readonly

    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
     const
    -0.09
    ior
    -0.09
    <dyn
    -0.08
     playoff
    -0.08
     è¾ĵ
    -0.08
    quet
    -0.08
    ishi
    -0.08
    eof
    -0.08
     missing
    -0.08
    POSITIVE LOGITS
    AMA
    0.10
    yte
    0.09
    ète
    0.08
    ama
    0.08
    verted
    0.08
     Mint
    0.08
    -bound
    0.08
    nic
    0.08
    thr
    0.08
    áb
    0.07
    Activations Density 0.007%

    No Known Activations