© 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. 58248
    Prev
    Next
    INDEX
    Explanations

    United States Court of Appeals descriptors

    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
    asel
    -0.09
     Cycl
    -0.08
    ifax
    -0.08
    ros
    -0.07
     Circ
    -0.07
    kest
    -0.07
    abus
    -0.07
    FER
    -0.07
    aven
    -0.07
     Trouble
    -0.07
    POSITIVE LOGITS
    ed
    0.13
    e
    0.11
    oled
    0.10
    eof
    0.10
    eus
    0.10
    IVATE
    0.09
    832
    0.09
     Ingram
    0.09
    oure
    0.09
    anka
    0.09
    Activations Density 0.003%

    No Known Activations