© 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. 1783
    Prev
    Next
    INDEX
    Explanations

    structural components, name attributes

    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
    uga
    -0.08
    elon
    -0.08
     shack
    -0.08
    [__
    -0.08
    SED
    -0.08
    (always
    -0.08
    ieux
    -0.08
    @student
    -0.08
    éra
    -0.08
    arkan
    -0.07
    POSITIVE LOGITS
    dash
    0.10
    lette
    0.10
     Rol
    0.10
     numbered
    0.10
    àµį
    0.09
     franchise
    0.08
     Auschwitz
    0.08
     Cory
    0.08
     \(
    0.08
     $
    0.08
    Activations Density 0.440%

    No Known Activations