© 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. 224
    Prev
    Next
    INDEX
    Explanations

    actions and states of being

    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
    +E
    -0.11
    iets
    -0.11
    /Error
    -0.11
     bö
    -0.11
    .springboot
    -0.11
    #index
    -0.11
    !!)↵
    -0.11
    .interval
    -0.11
    TEX
    -0.11
     acompañ
    -0.11
    POSITIVE LOGITS
    /generated
    0.09
    /do
    0.09
     when
    0.08
     during
    0.08
     concerning
    0.08
    /download
    0.08
    (ed
    0.08
     regarding
    0.07
     while
    0.07
    /use
    0.07
    Activations Density 1.159%

    No Known Activations