© 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. 145
    Prev
    Next
    INDEX
    Explanations

    sequence conditions or dependencies

    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
     extensively
    -0.12
     seperate
    -0.11
     libertine
    -0.11
     mainly
    -0.10
    dea
    -0.10
     nowadays
    -0.10
    æĶ¯
    -0.10
     fleece
    -0.10
    æł¸
    -0.09
     æĹ¥
    -0.09
    POSITIVE LOGITS
     corresponding
    0.13
     whichever
    0.12
     momentarily
    0.12
     exactly
    0.11
     whatever
    0.10
     corresponds
    0.10
     values
    0.10
     (
    0.09
     datap
    0.09
     instant
    0.09
    Activations Density 2.254%

    No Known Activations