© 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. 3628
    Prev
    Next
    INDEX
    Explanations

    small versions

    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
     massive
    -0.10
     Massive
    -0.10
     gigantic
    -0.09
     Largest
    -0.09
     trillion
    -0.09
     Giant
    -0.08
     Xxx
    -0.08
     enormous
    -0.08
    (and
    -0.08
     supreme
    -0.08
    POSITIVE LOGITS
     miniature
    0.15
    -lite
    0.14
     mini
    0.14
    Mini
    0.13
     tiny
    0.13
    mini
    0.13
    ette
    0.13
     small
    0.13
     Tiny
    0.12
    lets
    0.12
    Activations Density 1.001%

    No Known Activations