© 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. 8398
    Prev
    Next
    INDEX
    Explanations

    public opinion and vote

    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
     Rub
    -0.11
     Friendship
    -0.08
    oose
    -0.08
    eker
    -0.08
    -scalable
    -0.08
     wre
    -0.08
    Friend
    -0.08
    cia
    -0.08
    Rub
    -0.08
     RSVP
    -0.08
    POSITIVE LOGITS
     collectively
    0.10
     wisdom
    0.09
     kond
    0.09
     kits
    0.09
    .undo
    0.09
     Bain
    0.09
     domestically
    0.09
     nationally
    0.09
     packed
    0.09
    UTH
    0.08
    Activations Density 0.188%

    No Known Activations