© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 3148
    Prev
    Next
    INDEX
    Explanations

    author commentary on text

    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
     according
    -0.09
     scrolled
    -0.09
    according
    -0.09
    leta
    -0.09
     understood
    -0.09
     crud
    -0.08
     Benton
    -0.08
     spoke
    -0.08
    Bookmark
    -0.08
    CTR
    -0.08
    POSITIVE LOGITS
     Chapters
    0.14
     chapters
    0.14
     throughout
    0.13
    Throughout
    0.11
     Throughout
    0.11
     narrator
    0.11
     Chapter
    0.10
     chapter
    0.10
    Chapter
    0.10
     convinc
    0.09
    Activations Density 0.223%

    No Known Activations