© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 56807
    Prev
    Next
    INDEX
    Explanations

    with, with regard to, with open, with amazon

    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
    enie
    -0.09
    ils
    -0.08
    alm
    -0.08
     Malik
    -0.08
    Ñģл
    -0.08
    eger
    -0.08
    gal
    -0.08
     Kurd
    -0.08
    ais
    -0.08
    sembl
    -0.08
    POSITIVE LOGITS
    (optional
    0.10
    emos
    0.09
    werk
    0.09
    langs
    0.09
    babel
    0.08
    uze
    0.08
    (<
    0.08
    .placeholder
    0.08
    zier
    0.08
    AIT
    0.08
    Activations Density 0.088%

    No Known Activations