© 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. 54474
    Prev
    Next
    INDEX
    Explanations

    law of the case

    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
    amina
    -0.09
    roat
    -0.09
    osp
    -0.08
     disobed
    -0.08
     boot
    -0.08
    itarian
    -0.08
    ules
    -0.08
    anical
    -0.08
    uries
    -0.08
    us
    -0.08
    POSITIVE LOGITS
     Charl
    0.08
    ports
    0.08
    wich
    0.08
    iron
    0.08
    edom
    0.08
    aks
    0.08
    imet
    0.08
    -cookie
    0.08
    axed
    0.07
    imus
    0.07
    Activations Density 0.001%

    No Known Activations