© 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. 1833
    Prev
    Next
    INDEX
    Explanations

    circuit components and technical terms

    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
    ServiceProvider
    -0.08
     billions
    -0.07
     tempting
    -0.07
    ãĥ¼ãĥ«
    -0.07
     MILF
    -0.07
     levitra
    -0.07
     oficial
    -0.07
     gint
    -0.07
    XHR
    -0.07
    ,[],
    -0.07
    POSITIVE LOGITS
    :first
    0.10
     pip
    0.08
    .moves
    0.08
     (!((
    0.08
    innen
    0.07
    REATE
    0.07
    urname
    0.07
    uggling
    0.07
     sobie
    0.07
     fearless
    0.07
    Activations Density 6.546%

    No Known Activations