© 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. 57264
    Prev
    Next
    INDEX
    Explanations

    need to / assistance

    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
    hof
    -0.10
     Het
    -0.10
     faithfully
    -0.10
     Freak
    -0.10
    .cfg
    -0.09
    oku
    -0.09
     ATA
    -0.09
     Af
    -0.09
    spark
    -0.09
    вод
    -0.08
    POSITIVE LOGITS
     Forms
    0.08
     forms
    0.08
     fino
    0.07
     deltaTime
    0.07
     priceless
    0.07
     irresist
    0.07
    679
    0.07
    yal
    0.07
     superiority
    0.07
    ANGO
    0.07
    Activations Density 0.029%

    No Known Activations