© 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. 54000
    Prev
    Next
    INDEX
    Explanations

    panel discussion

    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
    -sl
    -0.12
    ABCDEFG
    -0.11
    INI
    -0.11
    ationale
    -0.10
    ulum
    -0.10
    bourg
    -0.10
    quia
    -0.10
    ophobia
    -0.10
    InSection
    -0.10
    arge
    -0.10
    POSITIVE LOGITS
     "
    0.07
     '
    0.07
    tur
    0.07
    åĨĮ
    0.07
     rel
    0.07
    isa
    0.07
     creators
    0.06
     created
    0.06
    asta
    0.06
     Westbrook
    0.06
    Activations Density 0.086%

    No Known Activations