© 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. 3381
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    pone
    -0.12
    @brief
    -0.11
    [".
    -0.11
    éo
    -0.11
    .online
    -0.11
    ¡°
    -0.11
    chio
    -0.11
    aeda
    -0.11
    chine
    -0.11
     Pays
    -0.10
    POSITIVE LOGITS
    xic
    0.07
     Estates
    0.06
     bo
    0.06
    (cx
    0.06
    ette
    0.05
    Li
    0.05
     cob
    0.05
     lip
    0.05
     deterministic
    0.05
    x
    0.05
    Activations Density 0.102%

    No Known Activations