© 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. 57085
    Prev
    Next
    INDEX
    Explanations

    summaries and representations

    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
    iners
    -0.10
     Bravo
    -0.09
    ango
    -0.09
    .Microsoft
    -0.09
    obe
    -0.09
     totalement
    -0.08
    NE
    -0.08
    otton
    -0.08
    SHARE
    -0.08
    shade
    -0.08
    POSITIVE LOGITS
     representative
    0.15
     summarized
    0.13
     summaries
    0.12
     condensed
    0.11
     summarize
    0.11
     summar
    0.11
     summary
    0.11
    atten
    0.10
     Hum
    0.10
     hum
    0.10
    Activations Density 0.104%

    No Known Activations