© 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. 2675
    Prev
    Next
    INDEX
    Explanations

    link, comments, follow, copyright

    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
    <|endoftext|>
    -0.11
     '\'
    -0.09
     pul
    -0.09
     elderly
    -0.09
     Sweep
    -0.08
    IMG
    -0.08
     Chase
    -0.08
     nag
    -0.08
    <![
    -0.08
     Dane
    -0.08
    POSITIVE LOGITS
     vej
    0.11
    fill
    0.08
    <tbody
    0.08
    illon
    0.08
     succesfully
    0.08
    alon
    0.08
     Hog
    0.08
    ocup
    0.08
    Keeper
    0.08
    åº
    0.07
    Activations Density 0.509%

    No Known Activations