© 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. 61513
    Prev
    Next
    INDEX
    Explanations

    point of view or character features

    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
     filmed
    -0.11
     film
    -0.10
     director
    -0.09
     portrayed
    -0.09
     films
    -0.09
     fict
    -0.09
     storyboard
    -0.09
     Bros
    -0.09
     imaginary
    -0.08
     alleg
    -0.08
    POSITIVE LOGITS
     chapters
    0.13
     chapter
    0.12
     Chapters
    0.11
     readers
    0.11
     reader
    0.10
     Chapter
    0.10
     Readers
    0.10
     typo
    0.09
     CHAPTER
    0.09
     Burgess
    0.09
    Activations Density 0.054%

    No Known Activations