© 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. 54616
    Prev
    Next
    INDEX
    Explanations

    static function declarations

    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
     histo
    -0.08
    eme
    -0.08
     impress
    -0.07
    utsch
    -0.07
    SA
    -0.07
     Waterloo
    -0.07
    oley
    -0.07
    isha
    -0.07
     sche
    -0.07
     ver
    -0.07
    POSITIVE LOGITS
    reste
    0.11
    esor
    0.10
     Activ
    0.10
     brows
    0.10
    FER
    0.10
    ån
    0.09
    -switch
    0.09
    urtles
    0.09
     activations
    0.09
    HELL
    0.09
    Activations Density 0.001%

    No Known Activations