© 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. 54654
    Prev
    Next
    INDEX
    Explanations

    after import or use

    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
     customizable
    -0.09
     creation
    -0.09
     rencontres
    -0.09
    STS
    -0.09
    åº
    -0.09
    ale
    -0.08
     theme
    -0.08
     customized
    -0.08
     pear
    -0.08
     purchase
    -0.08
    POSITIVE LOGITS
    undry
    0.09
    ilig
    0.09
    ousel
    0.09
     
    0.09
     Otherwise
    0.09
     Ther
    0.08
    endar
    0.08
    wagon
    0.08
    ibern
    0.08
    ertz
    0.08
    Activations Density 0.016%

    No Known Activations