© 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. 58862
    Prev
    Next
    INDEX
    Explanations

    highest rates, most vulnerable

    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
     widely
    -0.10
    igin
    -0.10
    广
    -0.09
    este
    -0.09
     widespread
    -0.09
     Worldwide
    -0.09
     everywhere
    -0.09
     Sw
    -0.09
    UDA
    -0.09
     Minority
    -0.09
    POSITIVE LOGITS
     fil
    0.09
    berg
    0.08
    cel
    0.08
     UserRepository
    0.08
     cul
    0.08
     Fil
    0.08
    venue
    0.08
    iners
    0.08
    ŀĭ
    0.07
    rai
    0.07
    Activations Density 0.040%

    No Known Activations