© 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. 3086
    Prev
    Next
    INDEX
    Explanations

    relative pronoun or preposition

    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
    uth
    -0.08
     detain
    -0.07
     ###
    -0.07
     Ñģо
    -0.07
    enberg
    -0.06
     besides
    -0.06
    ม
    -0.06
    illage
    -0.06
     served
    -0.06
     âĺħ
    -0.06
    POSITIVE LOGITS
    oller
    0.11
    ="<<
    0.10
    itra
    0.10
     shrink
    0.10
    &)↵
    0.10
     absol
    0.10
    acid
    0.10
    :',↵
    0.10
    indows
    0.10
     Unified
    0.10
    Activations Density 0.196%

    No Known Activations