© 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. 61588
    Prev
    Next
    INDEX
    Explanations

    appellant's brief or petition

    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
    edb
    -0.10
    rompt
    -0.10
    &e
    -0.10
    rud
    -0.10
    (each
    -0.10
    |#
    -0.10
    lined
    -0.10
    -basket
    -0.10
    éĢĢ
    -0.10
    byss
    -0.10
    POSITIVE LOGITS
     Controlled
    0.08
    SEN
    0.08
    Epoch
    0.08
     maj
    0.08
    imb
    0.08
    uses
    0.07
    ondon
    0.07
    Coach
    0.07
     Pen
    0.07
     culpa
    0.07
    Activations Density 0.006%

    No Known Activations