© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 54623
    Prev
    Next
    INDEX
    Explanations

    English language learning and grammar

    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
    stro
    -0.08
    icie
    -0.08
    097
    -0.08
    ìłģ
    -0.08
     dressing
    -0.08
    {*
    -0.08
    çķĮ
    -0.08
     Dress
    -0.08
     stirring
    -0.07
     vinc
    -0.07
    POSITIVE LOGITS
     English
    0.12
     Florian
    0.11
     ESL
    0.11
     learners
    0.10
    sink
    0.10
     prag
    0.10
     Fry
    0.10
     practise
    0.10
     idi
    0.10
     pronunciation
    0.10
    Activations Density 0.152%

    No Known Activations