© 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. 736
    Prev
    Next
    INDEX
    Explanations

    compound words endings

    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
    LOTS
    -0.10
    guards
    -0.10
    ï¸
    -0.10
    âĢ
    -0.09
     autoplay
    -0.09
    -spinner
    -0.09
    OWN
    -0.09
    outu
    -0.09
     busty
    -0.09
    atee
    -0.09
    POSITIVE LOGITS
     stuff
    0.16
     thing
    0.14
    -ish
    0.11
    whatever
    0.11
     ones
    0.11
     whatever
    0.10
    aaa
    0.10
     guys
    0.10
     anyway
    0.10
    -esque
    0.10
    Activations Density 3.359%

    No Known Activations