© 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. 58871
    Prev
    Next
    INDEX
    Explanations

    speaking, lecturing, sharing

    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
     volunteers
    -0.09
     volunteer
    -0.09
     nobody
    -0.09
     helpers
    -0.09
     Volunteer
    -0.08
     hire
    -0.08
     fun
    -0.08
    Swipe
    -0.08
     sw
    -0.08
     volunteering
    -0.08
    POSITIVE LOGITS
    ROL
    0.10
    ittel
    0.09
     errno
    0.09
     Revision
    0.08
    opic
    0.08
    hone
    0.08
    habit
    0.08
    ä½ķ
    0.08
    verse
    0.08
    ateria
    0.08
    Activations Density 0.055%

    No Known Activations