© 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. 58625
    Prev
    Next
    INDEX
    Explanations

    crawling or craw words

    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
    uate
    -0.10
    uations
    -0.09
    otti
    -0.08
    uating
    -0.08
     Trev
    -0.08
    ology
    -0.08
     grad
    -0.08
    uated
    -0.08
    ography
    -0.08
    arel
    -0.08
    POSITIVE LOGITS
    nest
    0.11
    ickers
    0.10
     wur
    0.09
    emon
    0.09
    iers
    0.09
    ehr
    0.09
    eyes
    0.09
    izable
    0.08
     Pars
    0.08
    .githubusercontent
    0.08
    Activations Density 0.007%

    No Known Activations