© 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. 54647
    Prev
    Next
    INDEX
    Explanations

    searching for answers

    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
     sublicense
    -0.09
     cal
    -0.08
    linger
    -0.08
    :',↵
    -0.08
     Burns
    -0.08
     Stir
    -0.08
    beck
    -0.08
     zg
    -0.07
     Styles
    -0.07
     Coff
    -0.07
    POSITIVE LOGITS
     Doyle
    0.10
    ria
    0.10
    inn
    0.09
     most
    0.09
    crypt
    0.09
    ioso
    0.09
     homosex
    0.09
     Hiring
    0.08
    uster
    0.08
     CONS
    0.08
    Activations Density 0.087%

    No Known Activations