© 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. 8425
    Prev
    Next
    INDEX
    Explanations

    don't want to accidently

    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
     almost
    -0.11
    shal
    -0.09
    iller
    -0.09
     Trou
    -0.09
     Unless
    -0.09
    illac
    -0.09
     warnings
    -0.09
     JQuery
    -0.09
     occasionally
    -0.09
     qual
    -0.08
    POSITIVE LOGITS
     accidentally
    0.12
     future
    0.08
     accident
    0.08
     inadvertently
    0.08
     Falling
    0.08
     anymore
    0.08
     inadvert
    0.08
     TOO
    0.08
     mistakenly
    0.08
     accidental
    0.08
    Activations Density 0.284%

    No Known Activations