© 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. 8336
    Prev
    Next
    INDEX
    Explanations

    LaTeX document structures

    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
     Ow
    -0.08
    ARB
    -0.08
     Creed
    -0.08
    ider
    -0.07
     trick
    -0.07
     Huff
    -0.07
     Hij
    -0.07
     Tango
    -0.07
    Stuff
    -0.07
     Former
    -0.07
    POSITIVE LOGITS
    endment
    0.09
    chin
    0.08
     abused
    0.08
    increment
    0.08
    .eu
    0.08
    ÑĪе
    0.08
     lect
    0.08
     ver
    0.08
    atu
    0.08
    -banner
    0.08
    Activations Density 0.006%

    No Known Activations