© 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. 990
    Prev
    Next
    INDEX
    Explanations

    relative clauses starting with which or where

    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
    [email
    -0.09
     onto
    -0.07
    azi
    -0.07
     whereas
    -0.07
    earer
    -0.07
    odor
    -0.07
    åľ¨
    -0.07
     when
    -0.07
    these
    -0.07
    iform
    -0.07
    POSITIVE LOGITS
    upon
    0.17
    fore
    0.15
    soever
    0.14
    ìĦľ
    0.13
    case
    0.13
     lies
    0.12
    ìĦ
    0.12
    on
    0.12
     lur
    0.11
     неÑĤ
    0.11
    Activations Density 1.347%

    No Known Activations