© 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. 57720
    Prev
    Next
    INDEX
    Explanations

    device ID and driver enumeration

    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
     censor
    -0.10
     Cot
    -0.10
     censorship
    -0.09
     cot
    -0.09
     Arm
    -0.08
    ìĤ°
    -0.08
    ils
    -0.08
    ende
    -0.08
    ophone
    -0.07
     Nurse
    -0.07
    POSITIVE LOGITS
     organic
    0.10
     specialization
    0.09
     Statue
    0.09
     specialize
    0.08
    attery
    0.08
     HID
    0.08
    urma
    0.08
    Enumeration
    0.08
     Organic
    0.08
     spare
    0.08
    Activations Density 0.019%

    No Known Activations