© 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. 2920
    Prev
    Next
    INDEX
    Explanations

    I, me, you pronouns before verbs

    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
     Alias
    -0.12
    ifs
    -0.10
    .dk
    -0.09
     Opr
    -0.09
    wap
    -0.09
    als
    -0.09
    ales
    -0.09
    -pdf
    -0.09
     lÃŃ
    -0.09
    alem
    -0.09
    POSITIVE LOGITS
    itr
    0.08
    mont
    0.08
    kn
    0.08
    671
    0.08
     puff
    0.07
     Hess
    0.07
     Giovanni
    0.07
    hab
    0.07
    éis
    0.07
    rium
    0.07
    Activations Density 0.372%

    No Known Activations