© 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. 53804
    Prev
    Next
    INDEX
    Explanations

    android AppCompatActivity

    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
     Nass
    -0.10
     еÑģÑĤÑĮ
    -0.10
    991
    -0.09
    achi
    -0.09
     Corm
    -0.09
     Arrest
    -0.08
    eder
    -0.08
    .github
    -0.08
     Tops
    -0.08
    vie
    -0.08
    POSITIVE LOGITS
    Mage
    0.07
     Marty
    0.07
     ANSI
    0.07
    wise
    0.07
     esper
    0.07
     doors
    0.07
     prone
    0.07
    dee
    0.07
     merchandise
    0.07
     Sus
    0.07
    Activations Density 0.001%

    No Known Activations