© 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. 54730
    Prev
    Next
    INDEX
    Explanations

    sang, recorded, toured, performing artists

    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
    ');↵↵↵↵
    -0.11
     project
    -0.11
    uments
    -0.11
    TED
    -0.10
     mobil
    -0.10
     cryptography
    -0.10
     handwritten
    -0.10
    /library
    -0.10
    err
    -0.10
    andal
    -0.10
    POSITIVE LOGITS
     dime
    0.09
     entert
    0.08
     profitable
    0.07
    rene
    0.07
     Paramount
    0.07
     amusement
    0.07
     subsidiary
    0.07
     manufacture
    0.07
     manufactured
    0.07
     melod
    0.06
    Activations Density 0.129%

    No Known Activations