© 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. 2987
    Prev
    Next
    INDEX
    Explanations

    and followed by names or "I"

    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
    éĩį
    -0.08
     Mystic
    -0.08
    owl
    -0.08
     similarly
    -0.07
     absence
    -0.07
     >::
    -0.07
     rebuilding
    -0.07
    ibel
    -0.07
     qt
    -0.07
    mith
    -0.07
    POSITIVE LOGITS
     euch
    0.10
     his
    0.09
    usize
    0.09
     hÃłng
    0.09
    ì¶ľ
    0.09
     Kinder
    0.09
     vers
    0.09
     company
    0.08
    adeon
    0.08
     fis
    0.08
    Activations Density 0.110%

    No Known Activations