© 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. 660
    Prev
    Next
    INDEX
    Explanations

    chemical compounds, technical terms

    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
    coli
    -0.09
    mlink
    -0.09
     Wer
    -0.08
    alla
    -0.08
    onde
    -0.08
    IFA
    -0.08
    .TryParse
    -0.08
    áfico
    -0.07
    Lorem
    -0.07
    ork
    -0.07
    POSITIVE LOGITS
     *,↵
    0.11
     respectively
    0.09
    aman
    0.08
    agan
    0.08
     "{\"
    0.07
     oraz
    0.07
     {↵↵↵↵
    0.07
     \↵
    0.07
    bben
    0.07
    strstr
    0.06
    Activations Density 9.740%

    No Known Activations