© 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. 8737
    Prev
    Next
    INDEX
    Explanations

    Before Submitted

    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
     entitled
    -0.08
     Wolff
    -0.08
    Posted
    -0.07
    lip
    -0.07
     Fist
    -0.07
    ÑĤом
    -0.07
     Ballard
    -0.07
    anc
    -0.07
     titled
    -0.07
    arat
    -0.07
    POSITIVE LOGITS
    atte
    0.09
    enco
    0.09
    .mem
    0.09
    kit
    0.09
     Us
    0.09
    ören
    0.09
     Soft
    0.09
     Bench
    0.09
    ä½ľèĢħ
    0.09
    abei
    0.08
    Activations Density 0.126%

    No Known Activations