© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 886
    Prev
    Next
    INDEX
    Explanations

    what is the difference

    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
     probably
    -0.11
     many
    -0.10
     almost
    -0.10
    -many
    -0.10
     quite
    -0.09
     thankfully
    -0.09
     both
    -0.09
     several
    -0.09
     IMO
    -0.09
     very
    -0.09
    POSITIVE LOGITS
    ?↵↵
    0.30
    ?
    0.29
    ?↵
    0.28
    ?”
    0.26
    ?</
    0.26
    ?"↵↵
    0.25
    ?"
    0.25
    ?↵↵↵↵↵↵
    0.25
    ?č↵
    0.25
    ?↵↵↵
    0.25
    Activations Density 2.808%

    No Known Activations