© 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. 55988
    Prev
    Next
    INDEX
    Explanations

    high speed or frequency

    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
     stead
    -0.13
     cush
    -0.12
     steady
    -0.12
     slow
    -0.11
    ollo
    -0.11
    acher
    -0.11
     slower
    -0.10
     è¾ĵ
    -0.10
    ogn
    -0.10
     lowes
    -0.10
    POSITIVE LOGITS
     sharp
    0.11
     concentrated
    0.10
     sharply
    0.10
     Shar
    0.09
     lightning
    0.09
     focused
    0.09
     Sharp
    0.09
    sharp
    0.09
    implode
    0.08
     sharper
    0.08
    Activations Density 0.082%

    No Known Activations