© 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. 2290
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers in dates

    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
    es
    -0.15
    er
    -0.12
    ed
    -0.12
    ing
    -0.11
    ers
    -0.10
    th
    -0.10
    arily
    -0.10
    en
    -0.10
    ly
    -0.09
    y
    -0.08
    POSITIVE LOGITS
    	Copyright
    0.15
    peon
    0.12
    ony
    0.12
    ecure
    0.12
    aeper
    0.12
    ulfill
    0.11
    venture
    0.11
    eprom
    0.11
     ((!
    0.11
    -expand
    0.11
    Activations Density 0.102%

    No Known Activations