© 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. 4678
    Prev
    Next
    INDEX
    Explanations

    love and related contexts

    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
    ERA
    -0.10
    ics
    -0.09
    ILA
    -0.09
    tems
    -0.08
     adj
    -0.08
    Ñĩ
    -0.08
     Alley
    -0.08
     Sands
    -0.08
    Ùı
    -0.08
     Esk
    -0.08
    POSITIVE LOGITS
     Constit
    0.10
    rien
    0.09
    bomb
    0.09
     interests
    0.08
    jer
    0.08
    oris
    0.08
    -kind
    0.08
    ick
    0.08
    itur
    0.08
     Consum
    0.08
    Activations Density 0.082%

    No Known Activations