© 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. 55090
    Prev
    Next
    INDEX
    Explanations

    x64, Win, iphone, maternity, power

    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
    avo
    -0.09
     compressed
    -0.08
    ough
    -0.08
    ######
    -0.08
    achten
    -0.08
    AXB
    -0.08
    implicitly
    -0.07
     indef
    -0.07
    runtime
    -0.07
     dow
    -0.07
    POSITIVE LOGITS
     Pruitt
    0.09
    URAL
    0.09
    ider
    0.08
    abox
    0.08
    ession
    0.08
    ounder
    0.08
    POR
    0.08
    erule
    0.08
     Continental
    0.08
    .exchange
    0.08
    Activations Density 0.001%

    No Known Activations