© 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. 57869
    Prev
    Next
    INDEX
    Explanations

    legal proceedings and convictions

    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
     documenting
    -0.08
    opp
    -0.08
     factual
    -0.07
    OLUM
    -0.07
    quiv
    -0.07
    ember
    -0.07
    ucha
    -0.07
    orial
    -0.07
     numeric
    -0.07
     Lun
    -0.07
    POSITIVE LOGITS
     incentiv
    0.10
     effortlessly
    0.10
     inadvertently
    0.09
    ewan
    0.09
     str
    0.09
     Ka
    0.09
    iran
    0.09
    Ka
    0.08
     straw
    0.08
     seamlessly
    0.08
    Activations Density 0.004%

    No Known Activations