© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 3884
    Prev
    Next
    INDEX
    Explanations

    commentary on news, politics, and topics

    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
     Ranking
    -0.09
    dao
    -0.08
    ranking
    -0.08
    arResult
    -0.08
    lander
    -0.08
    rox
    -0.08
    gende
    -0.08
    "class
    -0.08
    ï¸
    -0.08
    -0.08
    POSITIVE LOGITS
     news
    0.13
     topics
    0.12
     weekly
    0.11
     occasional
    0.11
     interesting
    0.11
     anything
    0.10
     everyday
    0.10
     topical
    0.10
     updates
    0.10
    spir
    0.09
    Activations Density 0.703%

    No Known Activations