© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 57092
    Prev
    Next
    INDEX
    Explanations

    confiscate, forfeit, seize property

    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
    ERE
    -0.08
     Ferguson
    -0.08
     Sik
    -0.07
     fluoride
    -0.07
    ode
    -0.07
    dale
    -0.07
    aque
    -0.07
    ocode
    -0.06
    eni
    -0.06
     Pine
    -0.06
    POSITIVE LOGITS
     Coral
    0.11
    anter
    0.11
    anti
    0.11
    wick
    0.10
    ANTI
    0.10
     launder
    0.10
    _dead
    0.10
     Streets
    0.09
    iez
    0.09
     Corruption
    0.09
    Activations Density 0.001%

    No Known Activations