© 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. 58304
    Prev
    Next
    INDEX
    Explanations

    use an/a/the

    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
    ppe
    -0.08
    unky
    -0.08
    iper
    -0.08
     dub
    -0.08
    onne
    -0.08
     Kensington
    -0.08
     belie
    -0.08
    phis
    -0.08
     mies
    -0.08
     voices
    -0.08
    POSITIVE LOGITS
    'o
    0.09
     fug
    0.09
    ABI
    0.08
     ----
    0.08
    lobals
    0.08
    cribe
    0.08
    AMS
    0.08
     honeymoon
    0.08
     babe
    0.08
    ió
    0.08
    Activations Density 0.055%

    No Known Activations