© 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. 62024
    Prev
    Next
    INDEX
    Explanations

    `get` or `set` methods

    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
    Negative Logits
    elt
    -0.11
    ankind
    -0.10
    cab
    -0.09
     Stanley
    -0.09
     Conversely
    -0.08
     marsh
    -0.08
     shovel
    -0.08
    izzle
    -0.08
    avana
    -0.08
     subscript
    -0.08
    POSITIVE LOGITS
    ей
    0.08
     invol
    0.08
     informative
    0.08
     rag
    0.08
     escap
    0.08
     Vest
    0.08
     predis
    0.08
     Mix
    0.08
     Cow
    0.08
     Keywords
    0.08
    Activations Density 0.016%

    No Known Activations