© 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. 8564
    Prev
    Next
    INDEX
    Explanations

    punctuations followed by sentence starts

    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
     debido
    -0.08
    aine
    -0.08
     Busy
    -0.08
    Explanation
    -0.07
     Explanation
    -0.07
    ivec
    -0.07
    Pending
    -0.07
    ilig
    -0.07
     prick
    -0.07
    roe
    -0.07
    POSITIVE LOGITS
    zu
    0.10
     Ideally
    0.10
     Samar
    0.10
     Sonia
    0.09
    AEA
    0.09
     focusing
    0.09
    onto
    0.09
    eni
    0.09
     Renault
    0.09
    -pos
    0.09
    Activations Density 0.454%

    No Known Activations