© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 2521
    Prev
    Next
    INDEX
    Explanations

    code constructs and keywords

    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
     Perkins
    -0.08
    ubar
    -0.07
     <=>
    -0.07
    uba
    -0.07
    ee
    -0.07
     fam
    -0.07
    <|fim_middle|>
    -0.07
    acre
    -0.07
     civil
    -0.07
    Ess
    -0.07
    POSITIVE LOGITS
    legen
    0.11
     thereof
    0.11
     bund
    0.10
    alah
    0.10
     therein
    0.10
     nad
    0.10
    antis
    0.10
    izia
    0.10
    eli
    0.09
     bottleneck
    0.09
    Activations Density 0.169%

    No Known Activations