© 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. 1926
    Prev
    Next
    INDEX
    Explanations

    verbs ending in ized/ulated followed by by

    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
    orang
    -0.13
    ebb
    -0.12
    ingleton
    -0.12
     cerco
    -0.12
    eft
    -0.11
    dee
    -0.11
    _Ass
    -0.11
    @student
    -0.11
    (any
    -0.11
    (PHP
    -0.11
    POSITIVE LOGITS
     by
    0.27
    by
    0.14
    _by
    0.13
     oleh
    0.13
     anew
    0.10
     into
    0.10
     via
    0.10
    /re
    0.10
    /shared
    0.10
     as
    0.10
    Activations Density 1.851%

    No Known Activations