© 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. 58189
    Prev
    Next
    INDEX
    Explanations

    opening files and reading modes

    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
    aker
    -0.08
    antine
    -0.08
    lez
    -0.08
    leck
    -0.07
     kin
    -0.07
     moto
    -0.07
    antic
    -0.07
    ember
    -0.07
     diplom
    -0.07
     bet
    -0.07
    POSITIVE LOGITS
     Sv
    0.10
     FileMode
    0.10
    Ear
    0.09
    riel
    0.09
    tra
    0.09
    _RDONLY
    0.09
     Forget
    0.09
    ër
    0.08
    ORE
    0.08
    ilib
    0.08
    Activations Density 0.006%

    No Known Activations