© 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. 1255
    Prev
    Next
    INDEX
    Explanations

    get updates

    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
    AndGet
    -0.12
    _get
    -0.11
     getting
    -0.10
     gotten
    -0.10
    Current
    -0.09
     Platt
    -0.09
    Courses
    -0.08
     Sanity
    -0.08
    ä¿
    -0.08
    CurrentValue
    -0.08
    POSITIVE LOGITS
     rid
    0.33
    tin
    0.19
    tings
    0.18
     Started
    0.18
     Rid
    0.17
    chas
    0.17
     started
    0.17
     hold
    0.17
     acquainted
    0.16
     involved
    0.16
    Activations Density 0.500%

    No Known Activations