© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 57008
    Prev
    Next
    INDEX
    Explanations

    mathematical definitions and evaluations

    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
    odem
    -0.08
     hem
    -0.08
    assel
    -0.08
    ìħ
    -0.08
    odo
    -0.08
    cate
    -0.08
    (IOException
    -0.08
     flip
    -0.08
    gc
    -0.08
    w
    -0.08
    POSITIVE LOGITS
     Lynn
    0.09
     TIMEOUT
    0.08
    Null
    0.08
     Marg
    0.08
    ixa
    0.08
    667
    0.08
    à¤ķ
    0.08
     Stock
    0.08
    lets
    0.08
     casc
    0.08
    Activations Density 0.009%

    No Known Activations