© 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. 3156
    Prev
    Next
    INDEX
    Explanations

    number after comma

    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
     Walter
    -0.09
     NSK
    -0.09
     Archives
    -0.08
    ards
    -0.08
    (NS
    -0.08
    OUGH
    -0.08
     Breaking
    -0.08
     Queens
    -0.07
    PA
    -0.07
    ANO
    -0.07
    POSITIVE LOGITS
    Locker
    0.09
     afterwards
    0.09
     samo
    0.09
    EMA
    0.09
    idle
    0.09
     Idle
    0.09
    riel
    0.08
     unlocked
    0.08
     Alta
    0.08
     Locker
    0.08
    Activations Density 0.114%

    No Known Activations