© 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. 53997
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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
     polic
    -0.10
    inus
    -0.10
    aben
    -0.10
    igu
    -0.10
    lec
    -0.09
    oso
    -0.09
    agrams
    -0.09
    ham
    -0.09
     Feather
    -0.08
    aton
    -0.08
    POSITIVE LOGITS
    undra
    0.08
    gli
    0.08
     wound
    0.08
     differential
    0.08
     mun
    0.08
     trif
    0.08
    ulla
    0.08
    pler
    0.07
    ffer
    0.07
     zab
    0.07
    Activations Density 0.034%

    No Known Activations