© 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. 54424
    Prev
    Next
    INDEX
    Explanations

    quash, overturn, repeal, reverse, stop, undo

    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
    ibo
    -0.10
     pres
    -0.10
     Died
    -0.09
    oose
    -0.09
     hal
    -0.08
    aber
    -0.08
     Breed
    -0.08
    oui
    -0.08
     Freed
    -0.08
    ule
    -0.08
    POSITIVE LOGITS
    anted
    0.09
    ë³
    0.09
    ry
    0.09
     Signing
    0.09
    rina
    0.08
     cree
    0.08
     Roll
    0.08
     Invasion
    0.08
    sburg
    0.08
     keer
    0.08
    Activations Density 0.004%

    No Known Activations