© 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. 58471
    Prev
    Next
    INDEX
    Explanations

    Chinese quotes

    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
    unks
    -0.11
    ont
    -0.10
     Lives
    -0.09
    UNK
    -0.09
    ktop
    -0.09
    Ñİ
    -0.09
    unk
    -0.09
    ant
    -0.09
    á»Ļ
    -0.08
     Hipp
    -0.08
    POSITIVE LOGITS
    ly
    0.13
    s
    0.11
    ONA
    0.08
    ollo
    0.08
     freshmen
    0.08
    anela
    0.08
     Gust
    0.07
    /se
    0.07
     Tucker
    0.07
    /per
    0.07
    Activations Density 0.044%

    No Known Activations