© 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. 4752
    Prev
    Next
    INDEX
    Explanations

    dialogue punctuation followed by speech

    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
    ash
    -0.09
    OI
    -0.08
    oi
    -0.08
    áb
    -0.08
     referring
    -0.08
     descriptions
    -0.08
    ."
    -0.08
     refer
    -0.08
    bek
    -0.08
    alom
    -0.08
    POSITIVE LOGITS
     Says
    0.10
    онÑĤ
    0.10
     says
    0.10
    orea
    0.10
    says
    0.09
    usher
    0.09
    ÙĬر
    0.09
    mates
    0.09
    umbo
    0.09
    uss
    0.09
    Activations Density 0.090%

    No Known Activations