© 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. 58571
    Prev
    Next
    INDEX
    Explanations

    Russian verb endings and suffixes

    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
    ãģķãĤĮ
    -0.10
    ed
    -0.09
     yourself
    -0.09
    adm
    -0.08
    edBy
    -0.08
    ised
    -0.08
     by
    -0.08
     rol
    -0.08
    edly
    -0.08
     amb
    -0.08
    POSITIVE LOGITS
    ÑİÑī
    0.14
    ÑĥÑİÑī
    0.11
     Pey
    0.10
    issing
    0.10
    ingo
    0.10
    lik
    0.10
    STANCE
    0.10
    ingly
    0.10
    ptime
    0.10
    rand
    0.09
    Activations Density 0.154%

    No Known Activations