© 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. 67
    Prev
    Next
    INDEX
    Explanations

    world’s, world may, world leader

    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
     nationwide
    -0.10
    LOS
    -0.09
    _globals
    -0.09
     Nationwide
    -0.09
     Ting
    -0.08
     Casc
    -0.08
    field
    -0.08
     statewide
    -0.07
    oup
    -0.07
     comb
    -0.07
    POSITIVE LOGITS
    -wide
    0.22
    wide
    0.19
    -ren
    0.19
    Wide
    0.17
     Wide
    0.17
     wide
    0.16
    wid
    0.15
    /world
    0.14
    views
    0.14
    -class
    0.13
    Activations Density 0.821%

    No Known Activations