© 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. 54566
    Prev
    Next
    INDEX
    Explanations

    return keywords and code structures

    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
     reliance
    -0.09
     accustomed
    -0.08
    allee
    -0.08
     servi
    -0.07
    kowski
    -0.07
     yaÅŁ
    -0.07
     or
    -0.07
     rely
    -0.07
    odie
    -0.07
     reliant
    -0.07
    POSITIVE LOGITS
    ROUT
    0.10
    contrib
    0.09
    lify
    0.09
     contrib
    0.09
    explicit
    0.09
    kit
    0.09
    -export
    0.09
     kits
    0.09
    .fi
    0.09
    bih
    0.09
    Activations Density 0.002%

    No Known Activations