© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 4032
    Prev
    Next
    INDEX
    Explanations

    backing vocals

    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
    ámara
    -0.08
    âĢ¦↵↵
    -0.08
     blinking
    -0.07
     Antoine
    -0.07
     âĢ¦↵↵
    -0.07
     either
    -0.07
     mant
    -0.07
     dome
    -0.07
     similarly
    -0.07
     Cob
    -0.07
    POSITIVE LOGITS
     Invent
    0.09
    prs
    0.09
    ligt
    0.08
     Sax
    0.08
    lear
    0.08
    eca
    0.08
     ocas
    0.08
    ;br
    0.08
    oder
    0.08
     unde
    0.08
    Activations Density 0.065%

    No Known Activations