© 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. 53738
    Prev
    Next
    INDEX
    Explanations

    RODUCTION

    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
     Jenn
    -0.08
     mutual
    -0.07
     Coff
    -0.07
     discovery
    -0.07
     instances
    -0.07
     taxing
    -0.06
     Discover
    -0.06
    villa
    -0.06
     Kimber
    -0.06
    UI
    -0.06
    POSITIVE LOGITS
    inci
    0.12
    oller
    0.11
    omba
    0.11
    енÑĤ
    0.11
    lar
    0.10
    ÑģÑĤва
    0.10
     Gareth
    0.10
     Minds
    0.10
    ...</
    0.10
    eye
    0.10
    Activations Density 0.002%

    No Known Activations