© 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. 54
    Prev
    Next
    INDEX
    Explanations

    sequence starters

    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
     Died
    -0.09
     candidate
    -0.08
    irl
    -0.08
     Pee
    -0.08
     Dont
    -0.08
     Definitely
    -0.08
     Cater
    -0.08
     Himself
    -0.08
    avin
    -0.07
     drifted
    -0.07
    POSITIVE LOGITS
     furthermore
    0.13
     There
    0.12
     moreover
    0.12
     incompet
    0.11
     If
    0.11
     However
    0.11
     meanwhile
    0.11
     there
    0.11
     When
    0.10
     This
    0.10
    Activations Density 1.521%

    No Known Activations