© 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. 54745
    Prev
    Next
    INDEX
    Explanations

    closing punctuation of 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
     sok
    -0.08
    aly
    -0.08
    omal
    -0.08
     clit
    -0.08
     belonging
    -0.08
    opt
    -0.08
    озд
    -0.08
    thew
    -0.08
    ķ
    -0.08
    )["
    -0.08
    POSITIVE LOGITS
     Signup
    0.09
    lings
    0.09
    oose
    0.08
     tarn
    0.08
    -II
    0.08
     internally
    0.08
    yaw
    0.08
     intro
    0.08
     newsp
    0.08
     dalle
    0.08
    Activations Density 0.110%

    No Known Activations