© 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. 993
    Prev
    Next
    INDEX
    Explanations

    prefix ending in 'te'

    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
    ness
    -0.24
    re
    -0.20
    so
    -0.20
    ship
    -0.18
    son
    -0.17
    set
    -0.17
    ser
    -0.17
    ne
    -0.17
    sh
    -0.17
    ting
    -0.17
    POSITIVE LOGITS
    Ìģ
    0.19
    aux
    0.19
    eeee
    0.17
    eee
    0.16
    iros
    0.15
    urope
    0.15
    lectric
    0.14
    urs
    0.14
    ffect
    0.14
    ño
    0.14
    Activations Density 4.362%

    No Known Activations